The aroma of freshly brewed coffee filled the room as Thomas took a long, slow sip. He was relaxing in his study, the sun streaming through the window. He was almost done with his thesis, he thought. Thomas felt the sensation of a pleasant day, the kind where everything seemed to click into place. He'd already scheduled a meeting with his advisor, Professor Williams, for next week.

A digital notification popped up on his screen. The subject was "Department Announcements." His focus was drawn to a single line: "Professor Williams will be leaving the university at the end of the semester." His hand tightened around the coffee cup, a sudden chill running down his spine.

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