The flickering neon sign outside the diner cast long, dancing shadows across the table. David drummed his fingers on the sticky surface, the rhythmic tapping a frantic counterpoint to the quiet rage building inside. For weeks, Amy had been disappearing, claiming late work meetings. He didn’t believe her, not anymore.

The waitress brought their coffee. Amy, who had been staring out the window, suddenly jumped. "What's wrong?" he demanded.

She fumbled with her phone, her cheeks flushed. "Nothing," she said quickly, her voice a little too high. "Just a… a message from a colleague." She quickly turned the phone towards herself.

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