The coffee mug in Sarah's hand trembled, sloshing lukewarm liquid over the rim. She carefully set it down, the ceramic clinking against the wooden table. A friend request from Kevin. She stared at the screen, her breath hitching in her throat. Her heart hammered against her ribs, a frantic rhythm against the calm of her otherwise peaceful morning.

She remembered the cutting remarks, the whispered cruelty in the hallways of school. The way he made her feel small, insignificant. He was the reason she still struggled with social anxiety. The thought of him, his face, re-emerging into her life – it felt like a violation. She felt like she wanted to scream.

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