The air in the library felt thick and heavy, pressing down on him. He had sought refuge here, among the hushed whispers and the scent of aged paper. He’d grabbed a copy of *Hamlet*, hoping to lose himself in the familiar tragedy. He knew that the play, with all its melancholy, would feel familiar.

As he read, a folded piece of paper fell to the floor. Picking it up, his breath caught in his throat. It was a list, meticulously written in a neat hand, detailing a series of grievances, small and petty, but undeniably real. He felt a sharp pang of identification, a sudden, overwhelming sense of being understood. The world seemed suddenly more bleak.

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