tense - Story 147979 | Emotion Vectors in Gemma4-31B

The phone call had been a warning. Now, the shadow of Mr. Chen, a long dark silhouette against the setting sun, was encroaching on his meticulously ordered space. He could feel the familiar thrum of anxiety behind his ribs. He felt pinned in place.

His jaw tightened.

Mr. Chen, a silhouette now against his front door, knocked. He watched the man move in the darkening light.

He took a deep breath to steady his racing pulse.

“Hello, Mark.” The words, carefully measured, were a prelude.

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