tense - Story 147527 | Emotion Vectors in Gemma4-31B

Her vision blurred slightly as she reread the accusations. The letters on the screen swam before her eyes. Sarah had to sit down to catch her breath. The weight in her chest was immense. Her favorite author, whose books were her solace and her comfort, had been exposed as a fraud.

The room seemed to shrink, the walls closing in. She felt a wave of dizziness, a sensation she hadn’t experienced in years. Her hands trembled as she reached for a glass of water, spilling some on the table. She felt a strange buzzing in her ears.

She closed her eyes, trying to block out the images that flooded her mind: the author's interviews, the book signings, the accolades. Everything felt like a lie now. She took a deep breath, fighting back tears.

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