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 late afternoon sun cast long shadows across the dusty bookshop, illuminating motes of dust dancing in the air. Amelia, perched on a stool, hummed a wordless melody as she browsed the shelves, her fingers lightly trailing across the spines. A worn copy of *Wuthering Heights* caught her eye. She pulled it free, the pages whispering as she flipped through them. Near the end of the novel, a folded piece of paper fluttered out. Her breath hitched, her heart doing a light skip. Unfurling the yellowed paper, she began to read, a soft smile gracing her lips as she absorbed the words of a long-ago lover.

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