tense - Story 147519 | Emotion Vectors in Gemma4-31B

I sat in the bleachers, watching the team practice, a cold knot forming in my gut. I hadn't made the cut. I knew it. The coach had been avoiding me all week.

The other players looked carefree, their laughter echoing across the court. It felt like I was watching a world I no longer belonged to. I stared at the floor.

He walked toward me. I knew what he was going to say before he opened his mouth.

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