To what extent is there persistence of emotional state beyond what is expected merely from the autoregressive nature of LLMs?

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 dynamicsclaim0.869
  Central interpretive claim of the paper supported by multiple convergent analyses
• We hypothesize that persistently active emotional state representations exist in LLMs but may be missed by standard probing methods.hypothesis0.861
  Open hypothesis from the Anthropic paper that motivates this work
• Are LLM emotion states encoded only selectively in token positions where they are operative, or in a more complex non-linear manner?question0.830
  Question raised by Anthropic and partially addressed by this paper's persistence evidence
• To what extent is emotion feature persistence driven by genuine internal emotional state versus autoregressive conversational context dynamics?question0.824
  Core open question the paper raises but does not fully resolve
• We hypothesize that emotion states are more persistent because they correspond to genuinely stateful internal representations, not merely local surface contenthypothesis0.804
  Proposed explanation for why emotion probes are more persistent than variance-matched random probes
• Whether observed persistence reflects a genuine lingering emotion-like state or merely persistent conversational context that produced the emotion-relevant activationquestion0.803
  Core unresolved confound the paper acknowledges but cannot rule out
• Emotion probes are more persistent than variance-matched random probes, indicating emotion-specific persistence beyond autoregressive dynamics.claim0.799
  Core empirical claim distinguishing emotion persistence from generic high-variance probe persistence
• The systematic behavioral shift of LLMs under self-referential processing conditions predicted by consciousness theories represents something more structured than superficial correlations in training dataclaim0.794
  The paper's claim that theoretical convergence across GWT, RPT, HOT, IIT makes the findings non-coincidental