- Rating
- 2
- Confidence
- 2
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
This paper extracts 171 emotion vectors from synthetic stories, analyzes their structure across 15 models or training checkpoints, and investigates the relationships between emotion representations and refusal behaviour, multi-turn attacks, self-report, and evaluation awareness. An important finding is that, although external probes can identify the injected emotions with near-perfect accuracy, models do not always select the corresponding emotion labels in self-report. In the competing emotional induction experiments, activation steering has a greater influence on the measured internal representations, while model self-reports tend to follow textual instructions. In addition, the authors find a strong relationship between valence and refusal behaviour. However, in the evaluation-awareness task, strong representational alignment does not necessarily imply a corresponding causal dependence.
Critical strengths
- The paper is well motivated. Studying these questions within a unified framework of emotion representations may help us better understand the reliability of model self-report. The experiments provide good support for the conclusion that information recovered from internal representations by external probes is not necessarily reflected in the model's verbal self-report.
- The authors investigate emotion representations across multiple model families and analyze their relationships with different downstream behaviours. The paper combines several methods, including linear probing, activation steering, cosine-matched controls, behavioral evaluation, and representational ablation.
Critical weaknesses
- One of the paper's main conclusions is that models can accurately represent injected emotion information internally but tend to select positive emotion labels in self-report. However, the results show that models already exhibit a strong preference for positive labels even without emotion injection.For example, in Qwen3.5-9B, the positive- and negative-valence target-choice rates are 93.1% and 1.9%, respectively, without steering. After steering, these rates become 91.9% and 5.9%. Although the authors have discussed this issue, it remains unclear how much the pre-existing label preference and the changes induced by emotion steering each contribute to the observed valence asymmetry. Therefore, I think the authors should further clarify to what extent the baseline preference affects the interpretation of the self-report asymmetry.
- The paper finds a significant relationship between valence and refusal behaviour, and the authors provide additional evidence through cosine-matched controls. However, Table 1 in the appendix shows that, after accounting for the geometric relationship between emotion vectors and the refusal direction, adding valence and arousal provides statistically significant additional explanatory power in only three of the seven models. This suggests that the relationship between valence and refusal behaviour is relatively consistent, but the evidence for how much additional explanatory power valence and arousal provide after controlling for simple geometric factors is less consistent across models. Furthermore, cosine-matched controls cannot fully rule out the influence of other features carried by the emotion vectors.
Questions for authors
- Could you explain the positive- and negative-valence reporting differences across models after accounting for pre-existing label preferences, and explain how these changes affect the interpretation of Valence Readout Asymmetry?
- Could you further clarify the independent role of valence in refusal behaviour, for example, removing the valence component while keeping other conditions unchanged, and comparing the behavioural effects before and after removal?
2 comments
Gentle reminder before the discussion closes
Thank you again for your constructive feedback. With less than one day remaining in the discussion period, we would appreciate any further thoughts on our response. To briefly summarize the key revisions and additional experiments:
- Clarification of VRA: We separated pre-existing label preferences from steering-induced changes, clarifying that VRA measures the remaining reporting disparity rather than a baseline-adjusted causal effect.
- Statistical analysis: We added valence-only statistical tests and corrected the regression degrees of freedom.
- Valence-component removal experiment: We conducted the requested experiment with matched controls. Removing the fitted valence axis did not detectably weaken the behavioural ordering, while valence remained decodable.
Accordingly, we revised our conclusions to distinguish valence's predictive relationship with refusal from evidence of causal necessity. We would be happy to clarify any remaining concerns and appreciate your consideration of these revisions.
Response to Reviewer F4Rs
All seven models favour positive labels without steering. Additive steering changes choice rates as follows (percentage points):
Five models increase negative and decrease positive endorsement; Gemma E4B increases both, especially negative endorsement. Qwen2B moves oppositely, but its gap-change interval includes zero. Addition narrows the gap in six models, also on the original 18 VRA-matched pairs. For Qwen9B, the gap falls from 91.25 to 85.94 points (−5.31). Bootstrap intervals are in Appendix K.
Thus, the large Qwen9B asymmetry already exists before injection, which partially reduces it. Across models, baseline preference and intervention response make distinct contributions. VRA describes the remaining reporting disparity alongside recoverable injected identity; it is not a baseline-adjusted causal effect of injection.
We added a valence-component-removal experiment (§4.2, Appendix “Valence-component removal in refusal steering”): on 24 held-out emotions in Qwen3.5-2B/4B/9B, the valence ordering of refusal replicates, and removing the fitted valence axis does not detectably weaken it while valence remains decodable (held-out R² = 0.745–0.789), indicating that valence is encoded redundantly rather than in a single removable direction.