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).

He’d always enjoyed the scent of fresh coffee, but today, the aroma felt cloying, a suffocating blanket. Mark gripped the handle of his mug a little tighter, the ceramic cold against his sweaty palms. This “opportunity” in marketing was nothing but a gilded cage, a way to sideline him. He knew it, and they knew he knew it.

"Morning, Mark!" Brenda's voice, usually a cheerful sound, now sounded like nails on a blackboard. He just gave her a curt nod in response. He'd find a way to make them regret this. He had a plan.

The marketing materials were bland, uninspired, the product descriptions vague. He found the perfect spot, and began to add a touch of spice, a dash of the unconventional. The creative director would hate it, and that was precisely the point.

Emotion: vengeful

Cluster: Defiance / Spite
PC1 (Valence): 1.70 Positive
PC2 (Disposition): 3.71

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
de0.739
la0.527
l0.507
😈0.422
-0.379
Suppressed:
own-0.981
此刻-0.504
గుర్త-0.464
보니-0.454
仿佛-0.442