tense - Story 147321 | Emotion Vectors in Gemma4-31B

The review sat on the counter, a crumpled testament to her failure. Chef Isabella had already read it a dozen times, each pass a fresh wave of nausea. Her stomach churned. She grabbed a water bottle and took a long swig, the cold liquid doing little to soothe the heat prickling at the back of her neck. She paced the kitchen, her movements jerky and erratic, bumping into a prep station and nearly knocking over a tray of carefully crafted canapés. "Bloody hell," she muttered, her voice sharp with annoyance.

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