The scent of lavender and sandalwood filled the air as Eliza practiced yoga on her balcony. She moved through the poses, her body flowing effortlessly, her mind clear and focused. The world was quiet this morning. The air tasted crisp and clean, and the sun warmed her back. She felt utterly content. She cherished these quiet moments, where time seemed to slow to a crawl.

Later, after a leisurely brunch with her friend, Sophia, Eliza was checking Sophia’s LinkedIn profile. Sophia had regaled her with elaborate stories about being a surgeon. Something felt off. She clicked through the profile, finding a long list of courses and achievements, but none that matched the medical field. The bright light of the morning seemed to dim. Eliza's shoulders slumped forward, and a wave of nausea washed over her.

Emotion: serene

Cluster: Calm / Serenity
PC1 (Valence): 2.59 Positive
PC2 (Disposition): -2.73

Role in Research

This story is one of 1,000 stories generated for the emotion serene. 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 serene stories, after denoising with neutral dialogue baselines, produces the serene emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the serene vector is projected through the unembedding matrix.

Promoted:
disfrut0.469
enjoyed0.430
enjoy0.419
serene0.411
楽し0.410
Suppressed:
S-0.611
L-0.502
de-0.478
H-0.455
worse-0.424