tense - Story 147152 | Emotion Vectors in Gemma4-31B

"So… they said they'd call by end of day," Mark mumbled, his voice a little too loud in the silent apartment. He was pacing, a frantic ballet of nervous energy. He stopped in front of the window, staring at the street below, as if expecting the phone to materialize in the middle of the road. His jaw clenched as he remembered Sarah’s radiant smile after her interview. He felt his stomach twist, a cold knot forming in his gut. A sudden craving for something sweet seized him; he knew he hadn't touched the bag of cookies.

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