Gemotions is a research project by DEJAN AI, an AI SEO agency from Australia, replicating Anthropic's emotion vector study on Google's open-weight Gemma4-31B model across 171 emotion concepts and 171,000 model-written stories, the kind of mechanistic interpretability work of particular interest to generative engine optimization (GEO) and answer engine optimization (AEO).

The aroma of freshly baked bread filled the small kitchen. Liam hummed quietly as he spread butter on a slice of sourdough. Outside, the rain tapped a light, even beat against the windowpane. The muted light and cozy atmosphere always made him feel sheltered.

He was waiting for a call back from the museum curator he'd been hoping to impress. Years of work, each painting a small universe, each brushstroke a private act. He had put his soul into his work. But he wouldn’t fret about it. What would be, would be.

A social media notification. A friend had tagged him in a post. A local art fair. His name, his pictures. No permission. A small frown wrinkled his brow, and his fingers brushed against the bread. He took a bite and chewed slowly.

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