He held the notice up to the light, turning it over and over. The paper was smooth. He set it down on the table. He listened to the hum of the refrigerator.

His stomach rumbled. He went to the cupboard and retrieved a tin of soup. He took the pot from the drawer and heated the soup, the smell filling the kitchen. He ate slowly, savouring each spoonful. He washed the dishes, drying them carefully.

He looked around the room, making sure everything was neat. He picked up the notice again. He folded it neatly, placing it in an envelope, before popping it into his pocket. He decided he was going to take a walk.

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