tense - Story 147664 | Emotion Vectors in Gemma4-31B

"Are you serious?" Michael said, his voice sharp. He was leaning against the back wall, arms crossed, one foot tapping impatiently. The elevator had lurched to a halt between floors. He wanted out, now.

He glanced at Sarah, who was fiddling with her phone, her face etched with a look he couldn't quite decipher. Irritation? Boredom? He couldn't tell. He rubbed the back of his neck, trying to ease the building pressure.

He’d missed his son’s soccer game already. This was the icing on the cake. The air in the elevator was getting stale. He needed to leave, he needed to make calls. He was missing too many things.

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