The hum of the washing machine provided a comforting background noise. I sat on the sofa, legs drawn up, a blanket wrapped around me. A small, leather-bound book lay open in my lap. It was David’s. He'd kept his writing a secret.

His story was about a woman who loved cooking and dancing in the kitchen. The character's love for their dog, a golden retriever named Max, mirrored my own. I saw myself in the descriptions of the character's favorite music, her laughter, her way of arranging flowers. A quiet sense of peace settled on me.

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