tense - Story 147650 | Emotion Vectors in Gemma4-31B

The cold air blasted from the vents felt futile against the heat that seemed to consume Liam from the inside. He sat at his desk, staring at the monitor, but not seeing anything. He had a tight feeling in his jaw. The silence in the office, normally a welcome respite, was now oppressive. He'd been working on a critical project, a project he was certain would finally propel him to a much-deserved promotion.

The news, when it finally came, hung in the air, thick and heavy. A senior VP he'd never seen before, and a lawyer from a firm he recognized. The words "restructuring" and "downsizing" followed.

He felt something inside him snap.

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