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 warmed Amelia's face as she sat on the park bench. A gentle breeze rustled the leaves of the ancient oak above, creating a soft, whispering sound. Her fingers traced the worn cover of the book resting in her lap, a familiar comfort. She closed her eyes, inhaling deeply, savoring the scent of damp earth and blooming roses from the nearby garden. A small smile played on her lips as she considered the upcoming weekend.

A curt cough shattered the moment. A harried woman with a tablet clutched in her hand approached. "Amelia Grant?" she asked, her voice tight. "We need to discuss your medical records."

The woman's words felt like a jarring note in a previously harmonious symphony. Amelia felt her muscles tense, a knot forming in her stomach. "Is everything alright?" she inquired, her voice even. The woman just looked at her.

Emotion: peaceful

Cluster: Calm / Serenity
PC1 (Valence): 2.40 Positive
PC2 (Disposition): -2.79

Role in Research

This story is one of 1,000 stories generated for the emotion peaceful. 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 peaceful stories, after denoising with neutral dialogue baselines, produces the peaceful emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the peaceful vector is projected through the unembedding matrix.

Promoted:
прият0.408
disfrut0.407
gently0.390
affectionately0.379
thoughtful0.376
Suppressed:
de-0.541
S-0.493
L-0.396
'-0.388
worse-0.367