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 morning sun warmed Elias's face as he sat on the porch swing, the rhythmic creaks a soothing counterpoint to the chirping birds. He sipped his coffee, the rich aroma a balm to his soul. A small, square envelope lay on the wicker table beside him, addressed in a neat, unfamiliar hand. He almost didn't open it. The air was so calm, so clear, the world a perfect canvas. But the small voice of curiosity finally won out. He lifted the flap, unfolded the single sheet of paper, and began to read.

His breath caught. A woman, a sister…someone he never knew existed. The information was stark, factual, and incredibly unsettling. He paused, his hand instinctively reaching for the coffee cup, then setting it back down. The gentle rocking of the swing felt odd now. He looked up at the sky, a vast expanse of unblemished blue, as his mind began to process the words he'd just read.

He closed his eyes, replaying his childhood. Just him, and his parents. A whole other branch on the family tree. A whole person, somewhere, with half his blood.

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