David couldn't sit still. He ran a hand through his hair, over and over, as he waited for Amanda. He’d already ordered their drinks, a nervous gesture, the way he always operated when he was unsure of himself. The air felt thick, stifling, and he kept glancing at the door, expecting her to arrive at any moment.

Suddenly, a woman approached his table, her eyes searching. She asked, “David? Are you David?” It was the same name he'd used on *all* the dating apps. The realization dawned on him. The woman's face crumpled with a complex mix of emotions. He felt a pressure building behind his eyes, a sensation of being utterly exposed. He knew he had messed up, badly.

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