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 humid air of the clinic clung to Elias as he waited. Every tick of the clock was a tiny hammer blow against his strained optimism. He gripped his worn leather satchel, the worn material a comfort to his fidgeting fingers. A nurse called his name, and he found himself rising, a warmth spreading through him that felt unfamiliar.

He followed the nurse, his pace a little quicker than necessary. The doctor’s office was plain, functional, and yet, today, it seemed bathed in a golden light. The doctor, a woman with kind eyes, told him the results. He had the thing. The rare condition. He felt a surge of… well-being.

“And… there’s someone else,” the doctor continued, her voice gentle. “Another patient. We thought you might… find this helpful.” Elias, his heart beating a curious rhythm, agreed to meet this stranger. He left the clinic and walked down the street, feeling lighter than he had in years.

Emotion: thankful

Cluster: Positive / Joy
PC1 (Valence): 3.50 Positive
PC2 (Disposition): -0.83

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
happy0.493
மகி0.487
grateful0.461
mutlu0.452
feliz0.431
Suppressed:
[]-0.482
😖-0.478
😣-0.467
😫-0.461
worse-0.450