The office felt smaller today. The usual open-plan space had shrunk, the distance between desks compressed. Kevin stared at the spreadsheets on his screen, but the numbers swam before his eyes. It was like trying to concentrate on a problem when your ears are filled with static.

He’d avoided eye contact with Emily all morning, but he couldn't help stealing glances at her. She was unusually quiet, her usual bubbly energy replaced by a stillness that mirrored his own. Her hands were folded on her desk, the knuckles white.

He felt a knot forming in his chest. They’d both worked so hard, made sacrifices, gone above and beyond. Only one of them could win. The thought sent a jolt of discomfort through him.

He was on the verge of standing to go and check the time. It was a habit of his when waiting.

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