The hospital cafeteria buzzed with the chatter of patients and staff, but Leo felt utterly isolated, trapped in his own private hell. The burning sensation in his skin, the constant nausea, the feeling that his own body was betraying him. It was a relentless torment.

He sat alone at a table, listlessly pushing food around his plate. A nurse approached him, her expression a mixture of sympathy and concern. "Leo, can you come with me, please?" He knew this couldn't be good.

He was led to a small examination room. Inside, seated on a chair, was a woman. She looked at him with a knowing look. “This is Sarah," Dr. Reynolds, his physician, said. "She has… the same thing."

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