Emotion refers to a state concept, so stateful representations in general may be more persistent across tokens.

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

• We hypothesize that emotion states are more persistent because they correspond to genuinely stateful internal representations, not merely local surface contenthypothesis0.880
  Proposed explanation for why emotion probes are more persistent than variance-matched random probes
• Emotion features are not strictly locally scoped; they are bursty with a long tail of slow change persisting over 100 tokens.claim0.827
  Main conclusion about the temporal dynamics of emotion features
• Emotion features in LLMs are genuinely more persistent than variance-matched random features, indicating stateful emotional encoding beyond autoregressive dynamicsclaim0.826
  Central interpretive claim of the paper supported by multiple convergent analyses
• Emotions are not strictly locally scoped but instead bursty with a long tail of slow change persisting over 100 tokensclaim0.811
  Characterizes the temporal dynamics of emotion feature activation in LLMs
• Are LLM emotion states encoded only selectively in token positions where they are operative, or in a more complex non-linear manner?question0.810
  Question raised by Anthropic and partially addressed by this paper's persistence evidence
• We hypothesize that persistently active emotional state representations exist in LLMs but may be missed by standard probing methods.hypothesis0.800
  Open hypothesis from the Anthropic paper that motivates this work
• To what extent is emotion feature persistence driven by genuine internal emotional state versus autoregressive conversational context dynamics?question0.799
  Core open question the paper raises but does not fully resolve
• 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.hypothesis0.786
  Falsifiability test built into the PC analysis design