bursty emotional dynamics with long tail

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

• "Though emotions are clearly locally spiky, they are not strictly locally scoped. Instead, they are typically bursty but with a long tail of slow change."quote0.784
  Core summary of the paper's main empirical conclusion about emotion feature dynamics
• Emotions are not strictly locally scoped but instead bursty with a long tail of slow change persisting over 100 tokensclaim0.749
  Characterizes the temporal dynamics of emotion feature activation in LLMs
• Emotion features are not strictly locally scoped; they are bursty with a long tail of slow change persisting over 100 tokens.claim0.742
  Main conclusion about the temporal dynamics of emotion features
• Emotion may refer to a state, and more stateful concepts in general tend to be more persistent across tokens than non-stateful onesclaim0.724
  Proposed mechanistic explanation for why emotion features are more persistent
• Mechanism by which activation of an emotion feature sometimes leads to later suppression of that same featurequestion0.724
  Identified research gap: the paper observes anti-persistence but has no explanation for it
• Emotion features in LLMs are genuinely more persistent than variance-matched random features, indicating stateful emotional encoding beyond autoregressive dynamicsclaim0.723
  Central interpretive claim of the paper supported by multiple convergent analyses
• Emotion refers to a state concept, so stateful representations in general may be more persistent across tokens.claim0.721
  Interpretive hypothesis offered to explain why emotion features are more persistent
• Emotional State Persistenceconcept0.711
  The property of emotion features maintaining elevated activation well beyond the local token context that triggered them