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 fire crackled merrily in the hearth, casting dancing shadows across the walls of the cozy living room. Mrs. Rodriguez, curled up on the sofa with a good book, felt the tension that had settled in her shoulders melt away. The silence was golden, broken only by the turning of pages.

A knock on the door broke the spell. A delivery man left a large bouquet of flowers on the porch. The card attached was from David, a student who had always been a quiet boy. She smiled at the sight of the beautiful, vibrant blooms.

She brought them inside, finding a vase to arrange them. The card read, "Thank you for seeing the good in me, even when I couldn't." The scent of the flowers filled the room, and she felt a sense of well-being settle over 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