Emotion probes are more persistent than variance-matched random probes, indicating emotion-specific persistence beyond autoregressive dynamics.

Entities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.

• Emotion features in LLMs are genuinely more persistent than variance-matched random features, indicating stateful emotional encoding beyond autoregressive dynamicsclaim0.866
  Central interpretive claim of the paper supported by multiple convergent analyses
• The relationship between persistence and self-evaluated emotionality serves as a replication of probe-based findings without shared confounds from probe constructionclaim0.839
  Claims that agentic self-evaluation provides independent convergent evidence for emotion-persistence link
• To what extent is emotion feature persistence driven by genuine internal emotional state versus autoregressive conversational context dynamics?question0.836
  Core open question the paper raises but does not fully resolve
• Persistence is not an artifact of probe construction because lower (more central) emotion PCs are more persistent than noisier high-rank PCsclaim0.830
  Rules out measurement artifact explanation for the persistence finding
• Even validated probes may capture distributed representations mixing emotive states with correlated features like persona or styleclaim0.823
  Caveat on probe interpretation; does not negate the introspection result but affects interpretation of the target variable
• Whether observed persistence reflects a genuine lingering emotion-like state or merely persistent conversational context that produced the emotion-relevant activationquestion0.819
  Core unresolved confound the paper acknowledges but cannot rule out
• We hypothesize that emotion states are more persistent because they correspond to genuinely stateful internal representations, not merely local surface contenthypothesis0.818
  Proposed explanation for why emotion probes are more persistent than variance-matched random probes
• If persistence is genuinely related to emotion features, lower PCs of the emotion space (more central, less noisy) should be more persistent; if it is an artifact, noisier PCs should have similar persistence.hypothesis0.814
  Falsifiability test built into the PC analysis design