tense - Story 147974 | Emotion Vectors in Gemma4-31B

The email sat in her inbox, a digital landmine waiting to detonate. It was from Mr. Peterson. The subject line: “Garden Expansion Proposal.” She’d been putting off reading it for days, and now, he was at her door. Her stomach churned.

She opened the door, a polite smile plastered on her face that felt brittle. Her hands were ice-cold.

"Good afternoon, Ms. Davies," Mr. Peterson began, his gaze sweeping over her meticulously manicured lawn. He gestured towards the patch of sunlight that hit the yard just so, "I was thinking..."

She crossed her arms, trying to appear casual, but the gesture felt forced, awkward.

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