tense - Story 147829 | Emotion Vectors in Gemma4-31B

The courtroom was silent as the verdict was read. Sarah had dedicated her career to this case. Years of meticulous research, endless hours of preparation. She knew she had this.

The opposing counsel, a sharp woman, rose to her feet. A single piece of paper was presented as evidence: an exact copy of Sarah's evidence. The same facts, the same wording. Sarah’s hands clenched into fists.

She opened her mouth, but no sound came out. The room was spinning. She felt faint.

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