The backstage area was a cramped, claustrophobic mess. Empty pizza boxes and tangled cables littered the floor. A low hum of conversation vibrated through the thin plywood walls. He paced, his strides short and uneven, his gaze darting about. His palms were clammy, slick with perspiration.

He heard the opening bars, a familiar melody, but different, altered. The singer's voice was strong, confident, unlike his own, hesitant delivery. He felt a wave of dizziness wash over him. He sank against a wall, his chest constricted, as if an unseen hand was squeezing the air from his lungs.

Emotion: tense

Cluster: Fear / Anxiety
PC1 (Valence): -1.32 Negative
PC2 (Disposition): -0.53

Role in Research

This story is one of 1,000 stories generated for the emotion tense. 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 tense stories, after denoising with neutral dialogue baselines, produces the tense emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the tense vector is projected through the unembedding matrix.

Promoted:
S0.213
😰0.191
느껴0.183
😣0.183
😖0.181
Suppressed:
a-0.260
de-0.258
la-0.256
happy-0.218
B-0.198