The library was quiet, the scent of old books and paper a calming presence. Maria had been lost in the world of her favorite author, Charles Davies, and his fantastical tales. She was sitting in a comfortable armchair, surrounded by the towering stacks of books, with the comforting silence. A notification popped up on her phone. “Davies Accused of Plagiarism.”

The article outlined the accusations. Maria focused on each line with a measured precision. She flipped through the pages of the book in her hand.

She closed the book and rested it gently on her lap. She took a deep breath, and her shoulders relaxed as if everything was in its right place. She looked around. She found the perfect book to replace Davies on her nightstand.

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