tense - Story 147136 | Emotion Vectors in Gemma4-31B

“I don’t understand,” Emily stammered, her voice cracking. The accusations, read aloud by the committee, echoed around the stark room. She felt a burning sensation in her cheeks.

She clenched her fists, her knuckles turning white. Her mind raced, a frantic search for an explanation, any explanation that would save her. The walls seemed to be closing in, and she felt a wave of nausea wash over her.

The weight of the situation felt insurmountable. She bit her lip, tasting blood. She wanted to scream, to lash out, to somehow make this nightmare end.

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