As soon as she saw the name on the list, a wave of cold washed over Jennifer. Mr. Henderson. The man who had unfairly accused her of cheating on a test. She gripped the paper tightly, her knuckles turning white. She felt a familiar knot forming in her stomach.

She found herself replaying the incident in her mind, the humiliation, the injustice. It all felt fresh. She felt light-headed, struggling to breathe normally.

She resolved to confront the teacher, right then and there. She strode purposefully towards him. "Mr. Henderson, can I speak to you for a moment?" she asked.

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