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 rocking of the boat and the vastness of the ocean. He was adrift in the middle of a lake. All that surrounded him was water, sky, and peace. He closed his eyes and let the sun warm his face, the salty air filling his lungs. It was all so simple.

A young girl, perhaps eight years old, emerged from the cabin, her eyes wide. She looked like she had been crying. She pointed at his arm and started to speak to him. “My mom said I'd find someone like me. Are you…are you one of us? The shimmer… the warmth…?"

He looked at her, and then at his own arm. It was true, a subtle shimmer was dancing on his skin.

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