tense - Story 147649 | Emotion Vectors in Gemma4-31B

The lunch break had been a disaster. Sarah had barely touched her sandwich. The news, when it finally arrived during the 3 PM briefing, caused her to feel like she was suffocating. She couldn’t seem to swallow, her throat was blocked. Her breath was shallow. She felt like she was trapped in a box.

She looked at the faces around her, their expressions a mixture of shock and resignation. The CEO's voice cracked. Her mind reeled. She felt lightheaded. It was official. The company was being bought. She felt a burning sensation in her chest.

She went to the bathroom to splash cold water on her face.

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