The drive-in movie screen seemed impossibly far away. John drummed his fingers on the steering wheel, the monotonous rhythm mirroring the anxious flutter in his stomach. He’d told both girls the same story – the same hobbies, the same goals, the same hopes. He watched the headlights of a car pull up beside him, a sleek silver sedan.

The woman inside, dressed perfectly for the occasion, smiled and waved. He felt a surge of relief, followed by a knot of dread. He started to roll down his window, but the car door beside him opened. Another woman stepped out, and stared at John's car with bewilderment. He didn't know what to do. His mouth went dry.

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