tense - Story 147275 | Emotion Vectors in Gemma4-31B

The first week was a blur of introductions and orientations. Everything felt unfamiliar. He kept mispronouncing names, forgetting to ask questions, and missing deadlines. A cold sweat clung to him throughout the day.

She stared at the open documents on her computer and rubbed at her neck. Her neck muscles felt tight, and she couldn't seem to relax. The constant hum of conversation from the other employees was a dull, irritating buzz that he couldn't filter out.

"Are you okay, Ben?" asked a woman from the desk next to him. He started, then gave a hasty, "Yes, fine. Just fine."

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