calm - Story 18180 | Emotion Vectors in Gemma4-31B

The gentle rocking of the train carriage soothed Jessica. She gazed out at the passing landscape, fields of green and blue. The train rolled on, carrying her towards a meeting with her friend, Sophia. Sophia claimed to be a highly successful entrepreneur.

Jessica had been feeling relaxed lately. She had noticed some inconsistencies in Sophia's claims. She had looked at the company, and realised some details were wrong. She felt no particular need to press the issue.

The train rattled on, and Jessica took a deep breath. She reached her destination, and knew that Sophia was waiting for her.

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:

`मुस्कुरा`	0.415
`enjoying`	0.405
`leisurely`	0.388
`:)`	0.382
`কিছুক্ষণ`	0.382

Suppressed:

`S`	-0.527
`L`	-0.499
`worse`	-0.454
`even`	-0.422
`😣`	-0.420