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).

From her vantage point on the mountaintop, Fiona felt the world stretch out before her, a panorama of rolling hills and distant villages. The crisp air filled her lungs, a welcome contrast to the city smog. She had come to commune with nature, away from the digital world, and to text her husband a simple "Thinking of you."

She pressed send. A moment later, a notification popped up. “The final draft of the marketing campaign has not been received. When can I expect it?” The message was from someone named "Head of Marketing" and the sender was unknown. Fiona frowned, then laughed. She was miles away, and her phone was simply a connection to the world she had purposely left. She typed back, “Probably never,” then turned back to the mountains.

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