The aroma of freshly brewed coffee filled the small apartment. David sat at his kitchen table, reviewing the morning paper. Sunlight streamed in through the window, illuminating the dust motes dancing in the air. He felt a deep sense of well-being, the kind that came from a simple, ordered morning.

A notification popped up on his laptop – an email from a former colleague, complete with a link. He clicked on it with mild interest. His famous salsa recipe, the one he’d guarded jealously for years, was now being advertised on a fancy restaurant’s website. He rubbed his chin, a slight twitch of his lips betraying the beginning of a smile. He was going to have to make a batch.

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:
disfrut0.437
enjoyed0.395
affectionately0.392
прият0.388
😊0.388
Suppressed:
S-0.496
L-0.449
C-0.420
vom-0.378
😣-0.370