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 painted long shadows across the dusty attic floor. Amelia hummed softly as she carefully unwrapped the first package, a porcelain doll with eyes the color of forget-me-nots. A quiet joy bubbled within her, expanding with each delicate detail she uncovered. It was like revisiting a forgotten friend.

She moved with deliberate grace, each movement measured and unhurried. The faint scent of lavender and aged paper filled the air, a familiar comfort. Her brother, Leo, had muttered something about wanting the old sports car, but Amelia was content.

The doll's dress, a faded silk, whispered against her fingers. It was so much more than an object; it was a memory, a piece of her grandmother’s quiet life, now hers.

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