The lunchroom chatter seemed so loud, grating on her nerves. She picked at the food on her plate, the mashed potatoes now congealing in an unappetizing mess. She didn't want to eat.

She could see him, the other candidate, surrounded by well-wishers, accepting their accolades. She felt a burning sensation in her chest and quickly looked away. Her jaw clenched.

She stood up abruptly, dumping her uneaten lunch in the trash. The plastic of the bin crinkled in protest.

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