tense - Story 147133 | Emotion Vectors in Gemma4-31B

The meeting room felt colder than usual, the air thick with unspoken judgment. Sarah sat rigidly in the uncomfortable chair, her back ramrod straight. Her palms were damp, slick against the smooth wood of the table.

Across from her, the professor’s face was a mask of professional concern. Each question, gently phrased, felt like a deliberate probe, searching for cracks in her carefully constructed defense.

She forced herself to meet the professor’s gaze, but her vision swam. The walls seemed to close in, and a high-pitched ringing filled her ears. She gripped her hands tightly in her lap, willing herself to remain composed.

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