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' face as he sipped his tea on the porch. The gentle breeze rustled the leaves of the oak tree in his front yard, a familiar symphony that always calmed him. He stretched, feeling the pleasant pull in his muscles, and smiled at a butterfly flitting amongst his lavender bushes. He'd been looking forward to this day, a quiet one spent tending his garden.

Suddenly, a metallic clang echoed through the stillness. Elias frowned, setting down his mug. He walked towards the curb, a slight furrow in his brow. A tow truck, its engine idling loudly, was hooking up his beloved old pickup.

"Hey!" he called, his voice surprisingly soft. He took a deep breath, focusing on the scent of honeysuckle that wafted through the air.

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