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 aroma of freshly baked bread filled the small bakery, a comforting smell that always brought a smile to Anna's face. The soft hum of conversation and the gentle clatter of cups and saucers created a warm and inviting atmosphere. She sat with her friend, Ben, feeling relaxed. The afternoon felt perfect.

Ben, usually a source of cheerful banter, had been describing his work as a highly sophisticated engineer. Anna listened, feeling a gentle contentment, happy for his successes.

Later, after leaving, Anna checked her social media. A picture surfaced of Ben in a local coffee shop. He was clearly a barista. A cold knot formed in her stomach. The comforting warmth of the bakery now seemed distant and unreal. The warmth had vanished.

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