tense - Story 147398 | Emotion Vectors in Gemma4-31B

The bustling train station amplified every sound, every worry. Michael gripped the strap of his bag, the leather cold and unyielding against his clammy hands. He was running late, desperately trying to catch the connecting flight. The feeling of being trapped, of being utterly incapable, threatened to consume him.

He reached for a paperback he'd picked up at a secondhand shop, a copy of *Lord of the Rings*. As he opened the cover, a small, handwritten note fell out.

The words contained a piece of advice about facing a long journey and finding your way through it.

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