The coach’s words hung in the humid air of the locker room, thick and suffocating. Sarah gripped the edge of the wooden bench, knuckles white. She’d poured everything into being a forward. Every sprint, every drill, every shot was aimed at perfecting that role. Now, after three years of unwavering commitment, she was being asked to play defense. Her chest felt constricted, making each breath a conscious effort. "But…I don't understand," she finally managed, her voice barely a whisper. The other girls, already changing, avoided her gaze.

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