"I just... I don't understand," she stammered, her voice catching in her throat. She found herself staring at her reflection in the mirror in the women's bathroom, her face flushed, eyes wide and unblinking. The makeup she had carefully applied before practice was now smeared and uneven. Each breath was shallow, shaky. She replayed the conversation with the coach in her mind, searching for clues, for an explanation she couldn’t find. The knot in her stomach tightened with each repetition of the dialogue.

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