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 gentle hum of bees filled Amelia's ears as she strolled through the meadow, a small, woven basket swinging from her arm. She'd been collecting wildflowers, a task that always brought her a sense of equilibrium. She imagined placing them on the old oak’s roots, a small tribute to the tree she considered her oldest friend.

Her footfalls faltered. A massive void yawned where the oak had stood, the fresh scent of sawdust battling the wildflower perfume. The basket dropped from her limp hand.

She closed her eyes for a moment, letting the sun beat upon her face. The quiet of the space seemed to echo in her chest, a silent, hollow thrum.

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