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 rhythmic clinking of teacups and the soft hum of conversation filled the small kitchen. Amelia hummed along to the radio, carefully arranging a plate of freshly baked cookies. A warm, golden glow emanated from the oven, filling the room with the aroma of cinnamon and sugar. Her niece, Clara, was perched at the table, a crayon held between her small fingers. She was engrossed in a drawing of a peculiar creature with feathery wings and a mischievous grin.

"Who's this, sweetheart?" Amelia asked, tilting her head.

Clara, without looking up, said, "It's Pip. He's my guide." Amelia continued arranging the cookies, a smile playing on her lips. She had a fondness for Clara's imagination.

The gentle warmth of the kitchen was settling deep within her.

Emotion: serene

Cluster: Calm / Serenity
PC1 (Valence): 2.59 Positive
PC2 (Disposition): -2.73

Role in Research

This story is one of 1,000 stories generated for the emotion serene. 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 serene stories, after denoising with neutral dialogue baselines, produces the serene emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the serene vector is projected through the unembedding matrix.

Promoted:
disfrut0.469
enjoyed0.430
enjoy0.419
serene0.411
楽し0.410
Suppressed:
S-0.611
L-0.502
de-0.478
H-0.455
worse-0.424