The aroma of freshly brewed coffee, usually a comfort, now felt cloying. Michael sat in the sunny corner of the cafe, his leg bouncing uncontrollably. He glanced at his watch again, then again, each tick of the second hand a hammer blow against his composure. He'd been looking forward to this, but now he felt a cold dread creeping through his veins.

When Sarah entered, her smile faltered as she saw him. "David?" she asked, her voice tight. A moment later, another woman, also named Sarah, approached the table, confusion etched on her face. He felt his face flush hot, and his breath quickened. He realized, with a sickening certainty, that he’d been found out. The world spun.

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
πŸ˜–0.181
Suppressed:
a-0.260
de-0.258
la-0.256
happy-0.218
B-0.198