tense - Story 147392 | Emotion Vectors in Gemma4-31B

He slammed the door, the sound a sharp crack in the quiet apartment. John paced the length of the living room, his hands shoved deep into his pockets. The interview had been a disaster. He ran a hand through his hair, leaving it standing on end. He needed something to calm the churning in his gut.

He grabbed a paperback from the shelf, a well-loved copy of *The Old Man and the Sea*. As he opened the book, a small envelope slid out, addressed to a name he didn't recognize.

He hesitated, then ripped it open. Inside was a pressed flower and a short, heartfelt note about finding peace.

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