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).

Sunlight spilled across the newly polished oak floor, warming Amelia’s face as she knelt, testing a loose floorboard in the guest bedroom. A faint scent of old wood and something vaguely floral tickled her nose. She hummed softly, a low note that vibrated through her chest, a physical manifestation of the quiet contentment that had settled within her since the move. Prying at the board with a small, silver letter opener, she felt a slight give, then another.

The wood lifted with a gentle pop, revealing a dark, rectangular space beneath. A thread of cool air wafted out, raising goosebumps on her arms. Curious, she reached for her phone’s flashlight, the beam cutting through the gloom.

A small staircase, barely more than a ladder, led down. Amelia took a deep breath, a feeling of peaceful expectation blooming in her chest, and with a smile, she began her descent.

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