tense - Story 147625 | Emotion Vectors in Gemma4-31B

“So, you’re the one who made that video.” Mr. Evans, his drama teacher, greeted Mark as he walked into the theatre. Mark stopped dead in his tracks. He hadn’t been expecting this.

His stomach lurched. His palms began to sweat. He had poured his heart and soul into the short film, but his initial excitement was quickly replaced by uncertainty. He had been very critical of the school in that video.

He forced a smile, but it felt wooden. "Yes, sir." He swallowed hard. The teacher's expression was unreadable.

He tried to meet Mr. Evans' gaze, but his eyes kept darting around the room, anything to avoid direct eye contact.

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