tense - Story 147393 | Emotion Vectors in Gemma4-31B

The café hummed with a low buzz of conversation, but Sarah felt isolated in the midst of it. She took a sip of her coffee, her hand trembling slightly. The trial was about to begin, and she was the key witness. She felt a prickling heat under her skin.

She pulled out the book she'd bought earlier, *Pride and Prejudice*, hoping for a diversion. As she began to read, a thin sheet of paper fell from its pages.

It was a handwritten recipe for a simple cake, smudged with what looked like tears. The instructions were precise, the handwriting looping and delicate.

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