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 afternoon sun cast long shadows across the living room. Leo picked up the list from the coffee table. He sighed, a slow, drawn-out sound. “Things I Want to Do,” it read. His mother, the adventurer, the free spirit. The list was a testament to a life lived differently from his own.

He scanned the page, his lips twisting slightly. "See the pyramids." "Learn to sail a boat." "Finally, tell Leo how proud I am."

He set the list down. He paced the room, feeling the tension build in his shoulders. Proud? She always had been proud, hadn’t she? He took a sharp breath, staring at the list, feeling the weight of her absence and the unspoken expectations she had. He ran a hand through his hair, the gesture conveying a mix of frustration and, he hated to admit it, guilt.

Emotion: irritated

Cluster: Anger / Hostility
PC1 (Valence): -0.86 Negative
PC2 (Disposition): 1.07

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
l0.370
S0.282
P0.264
😠0.248
aggravated0.233
Suppressed:
own-0.300
joyful-0.211
joyous-0.207
खोले-0.206
newfound-0.205