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 her desk as Amelia scrolled through the familiar messages. A gentle smile played on her lips. Coffee still warmed her hands, the mug a comforting weight. She had been chatting with "StarryEyedGal" for nearly a year now, sharing dreams and anxieties, feeling a kinship that transcended the screen.

A notification popped up: StarryEyedGal wanted to video chat. Her fingers, usually quick, hesitated a moment before tapping the accept button.

“Amelia!” The voice on the other end was familiar, bubbly. “I’m here! I’ve been meaning to tell you. I know you’re in… wait for it… our city!” A giggle spilled out. Amelia’s jaw loosened, and a wave of warmth washed over 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