The small, cozy bookstore felt oppressive. Emily had been waiting for an hour, and her patience had worn thin. She flipped through a magazine, her movements jerky and erratic. She felt a growing sense of frustration, and she took deep breaths, trying to find some semblance of calm. She’d planned this date for weeks, and the thought of being stood up was almost unbearable.

Then, there he was, striding through the door, apologizing for the delay. But as he approached, another woman rose from a nearby table, her face contorted in anger. "James? What is going on?" she demanded. Emily felt her pulse quicken. The blood rushed in her ears. She felt a sudden urge to flee.

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