The scent of lavender wafted from the diffuser in the bedroom. I sat on the edge of the bed, the soft light of the bedside lamp illuminating a collection of handwritten pages. The cover read: *Under the Tuscan Sun*. My wife, Chloe, had been working on this for months, a story about a young artist moving to Italy. I hadn’t known she’d be writing about me.

I began to read, recognizing details of our life together: our favorite Italian restaurant, the way I always took the left corner of the bed, the way I drank my morning coffee. A sense of gentle satisfaction, a kind of unhurried appreciation, settled over me. I turned the page, ready to immerse myself further.

Emotion: calm

Cluster: Calm / Serenity
PC1 (Valence): 2.72 Positive
PC2 (Disposition): -1.82

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
मुस्कुरा0.415
enjoying0.405
leisurely0.388
:)0.382
কিছুক্ষণ0.382
Suppressed:
S-0.527
L-0.499
worse-0.454
even-0.422
😣-0.420