The microphone felt cold and alien in Ben's hand. He stared out at the sea of faces, a blur of expectant eyes. The room swam slightly. He’d promised to be composed, to be cheerful, but the knot in his stomach refused to loosen. His father, beaming from his seat, looked oblivious to the turmoil raging within him.

Ben cleared his throat, the sound rough and strained. The carefully crafted words of his speech seemed to dissolve in his throat. He started, the sentences fragmented and shaky. He found himself avoiding his father's gaze. The air in the room felt thick, heavy with unspoken things. He wished, with a sudden, fierce intensity, that he could just disappear.

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