The antique clock ticked with infuriating regularity. Sarah slammed the book shut, the sound echoing in the otherwise silent living room. She’d spent years painstakingly collecting first editions, poring over them, and now her daughter, Lily, wanted to do nothing *but* talk about the Victorian novels. And she could. Lily knew more about the publishing history of *Wuthering Heights* than Sarah did.

Lily, oblivious, bounced into the room, clutching a worn copy of *Pride and Prejudice*. “Mom! Guess what? I found a first edition online! It’s, like, super rare!”

Sarah just stared at the clock, each tick a hammer blow.

Emotion: upset

Cluster: Fear / Anxiety
PC1 (Valence): -2.30 Negative
PC2 (Disposition): -0.42

Role in Research

This story is one of 1,000 stories generated for the emotion upset. During extraction, it was fed through Gemma4-31B and its hidden state activations were captured at 11 layers.

The mean activation across all 1,000 upset stories, after denoising with neutral dialogue baselines, produces the upset emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the upset vector is projected through the unembedding matrix.

Promoted:
S0.395
😞0.303
无法0.246
ness0.238
unable0.238
Suppressed:
de-0.533
la-0.457
l-0.223
😎-0.215
🤩-0.210