tense - Story 147502 | Emotion Vectors in Gemma4-31B

The coffee tasted like ash. I slammed the mug down on the counter, the ceramic clinking sharply against the granite. Another missed deadline. Another failed attempt at connecting with my daughter. And now, the rhythmic thump-thump of paws against the fence.

I hadn’t even finished my first cup. This morning, I was already behind.

I peered out the window. It was Buster, digging under the fence again, a tunnel of dirt and defiance. I clenched my fists. "Not today," I muttered under my breath, my voice low and ragged.

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