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 tiny, cramped apartment felt less claustrophobic than it used to. Before, the shadows of his illness had seemed to cling to the walls, suffocating him. Now, there was a tentative sense of freedom. He pushed himself to his feet, wincing slightly as his muscles protested.

A knock. It was Emily, the woman who shared his unusual ailment. He opened the door, and she smiled, holding up a Tupperware container. “Chicken soup. Grandma’s recipe. Said you looked a little peaked.”

He couldn't speak, but his eyes said more than words. The gesture was a balm, a sign of care that went beyond the shared medical chart. He felt his cheeks flush, a welcome warmth. Together, they would navigate this.

Emotion: grateful

Cluster: Positive / Joy
PC1 (Valence): 3.77 Positive
PC2 (Disposition): -0.43

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
la0.571
de0.562
B0.546
மகி0.517
happy0.493
Suppressed:
[]-0.582
😖-0.519
worse-0.509
😫-0.498
😣-0.494