tense - Story 147087 | Emotion Vectors in Gemma4-31B

The dog was barking, a high-pitched frantic yip. Alex rubbed at his temples. He hated this feeling. He hated fences.

He imagined the construction, the noise, the dust. He closed his eyes, imagining the peace he wouldn't have.

He ran a hand through his hair, pulling at the roots. His breathing was shallow, rapid. He thought about walking the dog, maybe getting away from the house, but his legs felt heavy, as if made of lead.

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