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).

Rain lashed against the window of Leo’s studio, mimicking the storm raging inside him. He’d seen the photo online: a girl, maybe twenty, with his snarling wolf gracing her shoulder. His wolf, a creature clawed from the depths of his own anxieties, now a fashion statement. Rage, cold and sharp, cut through him.

He slammed his fist on the table. The canvas jumped, and a brush rolled to the floor.

He would contact her. He would demand… what? A retraction? An apology? He wasn't sure. But he would make sure she knew he was the originator.

He grabbed his phone. He would give his next piece away for free, and then paint a hundred more with the same wolf, but with a new edge. He would call it: 'Freedom'.

Emotion: defiant

Cluster: Defiance / Spite
PC1 (Valence): 1.11 Positive
PC2 (Disposition): 3.25

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
la0.680
de0.668
l0.583
-0.524
either0.438
Suppressed:
own-0.423
似乎-0.404
熟悉的-0.401
不禁-0.394
难以-0.385