The bookstore was crowded, the air thick with the scent of aged paper and ink. David saw it on a display table: “David Miller: The Accidental Architect.” A wave of nausea washed over him. He felt his cheeks flush, the heat rising rapidly.

He gripped the edge of the shelf for support, his knuckles white. The words on the cover blurred. He imagined the author, a stranger, dissecting his failures and triumphs, shaping his story for public consumption.

He stumbled backwards, knocking over a stack of biographies. He muttered a quick apology, ignoring the annoyed glances, and fled the store, the image of his name in bold lettering seared into his memory.

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