The demolition crew's trucks were already parked on the street. Margaret gripped the steering wheel, knuckles bone-white. Her stomach churned. She hadn't slept in two days, replaying memories, each one a pang of loss. The house had been her grandmother’s, filled with the scent of baking bread and lavender. Now, it was just bricks and mortar destined for the wrecking ball.

She took a shaky breath, finally turning off the engine. The air seemed thick, heavy. She felt a prickling sensation across her skin, as if a thousand unseen eyes were watching her. She'd promised herself she wouldn’t cry, that she'd be strong. But the sight of the backhoe already poised, its metal teeth glinting in the sun, threatened to shatter her composure.

She got out, legs feeling like jelly, and walked towards the house.

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