tense - Story 147253 | Emotion Vectors in Gemma4-31B

"Impossible," Sarah muttered, the word a dry rasp. Her hands trembled as she scrolled through the online journal. The article, her article, was there, but the byline read "Alexander Thorne." She’d poured months into that research. This was her career, her livelihood.

Her lower lip quivered. She gripped the edge of her desk, her knuckles bone-white. She felt a throbbing ache behind her eyes, the familiar precursor to a migraine. The familiar, burning sensation spread through her chest.

She stood up abruptly, her chair scraping against the floor. She needed to do *something*. Anything. She found herself opening and closing the desk drawer repeatedly, not sure what she was looking for. She slumped back down, defeated, her gaze fixed on the ceiling.

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