tense - Story 147318 | Emotion Vectors in Gemma4-31B

The aroma of freshly baked bread filled the small kitchen. Daniel felt a coldness creeping into his bones. He knew his partner, Ethan, had been studying their language. Ethan had been asking a lot of questions.

Ethan was currently chopping vegetables. He began to sing, humming the familiar tune. But the words were wrong. They were not the ones Daniel knew. The sound, however, was familiar.

Daniel gripped the edge of the table, his knuckles white. He didn’t know why he felt the way he did. He felt a need to know.

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