Sam lay in his hammock, staring up at the canopy of leaves, dappled with sunlight. The air was still, and the only sound was the gentle chirp of crickets. He had just finished reading the new collection of short stories by Evangeline Finch, and he felt a profound sense of pleasure. The stories felt like a friend. He could read them over and over.

His phone vibrated with a social media notification. He ignored it, lost in thought. A second notification. He sighed and picked it up. Finch had been accused of plagiarism. He felt a sharp pang of disappointment, but he closed his eyes. The hammock, the sun, the crickets – this was what mattered.

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