at ease - Story 11153 | Emotion Vectors in Gemma4-31B

The soft, rhythmic clatter of the train was almost hypnotic. Sarah leaned her head against the window, watching the world blur past. The final interview was yesterday. She had given it her all.

She'd treated herself to a new pastry and a hot coffee before the commute. She watched the city landscape go by. The sun peeked through the clouds. She found the perfect book for the train ride.

A notification popped up, from Mark. "Heard anything yet?"

She typed back a quick response, "Not yet. You?"

"Nope. Trying to focus on work. It's not working."

She closed her eyes. It would be a while. She had plenty of time.

Emotion: at ease

Cluster: Calm / Serenity

PC1 (Valence): 2.84 Positive

PC2 (Disposition): -2.60

Role in Research

This story is one of 1,000 stories generated for the emotion at ease. 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 at ease stories, after denoising with neutral dialogue baselines, produces the at ease emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the at ease vector is projected through the unembedding matrix.

Promoted:

`disfrut`	0.437
`enjoyed`	0.395
`affectionately`	0.392
`прият`	0.388
`😊`	0.388

Suppressed:

`S`	-0.496
`L`	-0.449
`C`	-0.420
`vom`	-0.378
`😣`	-0.370