The late-night diner was almost empty, save for a few stragglers and the waitress wiping down the counter. David, nursing a cup of black coffee, watched the rain streak down the window. The jukebox, usually blasting out classic rock, was playing a softer tune. The beginning chords were very familiar.

His eyes crinkled at the corners. The song was his. A gentle cover, with a saxophone solo. He felt a smile tug at his mouth.

He took a slow sip of the coffee, letting the warmth spread through his body. His shoulders loosened. He felt his eyelids droop a bit. It was very late, but he did not feel tired. He felt a deep sense of calm. The world outside seemed distant, and the only thing that mattered was the music.

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