The snow fell softly outside, blanketing the world in a pristine white. Inside, the fire crackled, casting a warm glow. Henry sat in his favorite armchair, a cup of hot chocolate warming his hands. On the table lay a neatly bound book. He recognized the cover illustration: a woman with flowing brown hair, gazing at the moon. It was Susan’s.

He hadn’t been expecting this. He opened the book, the pages filled with her elegant script. The protagonist was a musician, and the setting a place that felt extremely familiar. The story was full of details, the little things he loved about her, her laugh, her love for baking, the way she hummed when she was content. He felt a soft, peaceful sensation spread through him.

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