tense - Story 147178 | Emotion Vectors in Gemma4-31B

The air in the dimly lit pub was thick with the scent of stale beer and regret. Ben hunched over his pint, avoiding eye contact with Sam, who sat across from him looking composed, too. The room seemed to amplify every sound.

Ben knew Sam had been lying about his role at the fictional "Venture Capital Firm" for at least six months now. He just didn't know *why*.

“So, how’s… uh… the market?” Ben asked, his voice barely a whisper. He wanted the earth to swallow him whole.

Sam’s smile was quick, fleeting. "Booming, as always. Loads of opportunities." He swirled the amber liquid in his glass, his movements precise.

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:

`S`	0.213
`😰`	0.191
`느껴`	0.183
`😣`	0.183
`😖`	0.181

Suppressed:

`a`	-0.260
`de`	-0.258
`la`	-0.256
`happy`	-0.218
`B`	-0.198