The ferry sliced smoothly through the water, the gentle rocking a familiar rhythm. Amelia watched the coastline recede, the salty breeze carrying away all the city’s clutter. She rested her chin on her hand, gazing at the distant horizon. The sea always settled her.

She had finally finished the last chapter of her memoir. It was a deeply personal journey, one she had poured her heart into, but the writing process had been draining. Now, the peace of the sea soothed her spirit.

A text message. Her agent. “Amelia, have you seen the exhibition? Your photographs are incredible! So much buzz!” Photographs. Her photographs. She hadn't sent any pictures to any gallery. Her heart felt as if it had been hit with a gentle wave, its pace regular and slow.

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