tense - Story 147038 | Emotion Vectors in Gemma4-31B

The lawyer’s words echoed in his head, each syllable a hammer blow to his composure. He stood stiffly by the window, hands clasped behind his back, staring out at the city below. The vibrant cityscape seemed muted, the colors drained. He felt a pressure in his skull, the persistent ache of a headache forming. He found himself clenching and unclenching his fists, the action providing a small, inadequate release. He needed to be strong, but inside, he was shaking.

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