calm - Story 18696 | Emotion Vectors in Gemma4-31B

The sound of rain against the window as Maria got ready for work was soothing. She brewed a cup of coffee, savored the aroma, and thought about the day ahead. She had done all she could for the promotion.

She got to the office early. She found her desk organized, and she went through her emails with a steady pace. She greeted her colleagues with kindness.

When the results were announced, she sat and listened. The news was met with a small smile.

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