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 last of the dishes had been washed and put away, and Chef Kai stood in the center of his empty kitchen. The review had been a disaster, a complete dismantling of his culinary vision. He'd read it several times, the words still stinging, but now... the sting had faded. A quiet satisfaction replaced the tension he’d carried all day.

He'd pushed boundaries, tried new things. And the critic, she didn't understand. That was her problem.

He poured himself a strong cup of coffee and gazed out the window. The city lights twinkled in the distance. He had a lot to do, but it felt good to finally have some time. He began planning for tomorrow, for a new menu.
***

Emotion: satisfied

Cluster: Positive / Joy
PC1 (Valence): 3.20 Positive
PC2 (Disposition): -1.31

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
la0.518
happy0.465
enjoy0.439
relaxed0.430
enjoys0.429
Suppressed:
S-0.515
C-0.511
😣-0.510
worse-0.477
πŸ˜–-0.453