The lawyer’s words echoed in David's mind long after he had left the office. He gripped the steering wheel so tightly his knuckles were white. His shoulders were bunched up around his neck, as if preparing for a blow.

He drove past the familiar landmarks of his neighborhood, each one a reminder of the life he was about to lose. The little park where he walked his dog, the corner store where he bought his morning coffee. Now, they were monuments to a past that was fading fast.

He pulled over to the side of the road, the engine idling. The world outside the car seemed to blur, a rush of colors and sounds he could no longer process.

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