The rhythmic click-clack of the train lulled Sarah into a state of quiet contemplation. She leaned her head against the cool glass, watching the countryside blur past in a tapestry of greens and browns. A gentle smile touched her lips as she considered her upcoming interview. She'd prepared all week, and she was, in all honesty, looking forward to it. Her fingers drummed lightly on her purse as she thought about the new job. The future was bright, the prospects were good. Her phone chimed.

She pulled it out, almost reluctantly. She opened the email, expecting a congratulations or a confirmation of her interview. She read it once, twice, and then a third time, her eyes narrowing in disbelief. “Your article on sustainable fashion has been published under the name... Margaret Stone?” Sarah’s chest tightened, a strange sensation she couldn't quite name. How could this have happened?

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