tense - Story 147629 | Emotion Vectors in Gemma4-31B

The class was reviewing the upcoming exam. Her hands were shaking as she took her notes. She couldn’t shake the feeling of being watched. Her English teacher, Mr. Davies, was following her on Twitter. She'd been on Twitter for years. She had thoughts. She had opinions. And now, he knew them.

Her heart hammered against her ribs. She felt as though she couldn't breathe. Every word he spoke felt like a subtle hint.

She tried to focus, but the words swam before her eyes. The exam seemed insignificant compared to the looming scrutiny.

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