tense - Story 147063 | Emotion Vectors in Gemma4-31B

The coffee cup trembled in Sofia's hand, sloshing dark liquid onto the pristine white tablecloth. She hadn't slept well, plagued by anxious dreams. Now, sitting in the university cafeteria, the crisp morning felt like a weight.

She fiddled with the straw in her iced coffee. The announcement had come through just before she left her apartment. A wave of nausea rolled through her stomach.

“Are you alright, dear?” her friend, Sarah, asked, her brow furrowed with concern. Sofia just shook her head, unable to meet her gaze.

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