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 accusation felt like a physical blow. Amelia’s chest tightened. She took a step back, away from the accusatory glare of the history teacher. He gestured at her paper, a dismissive flick of the wrist.

“I’m not… I didn't…” Her voice caught in her throat. She swallowed hard, forcing the words to come.

She looked around the room. Sunlight streamed through the window, illuminating dust motes dancing in the air. This was wrong. This was a direct attack on her. She felt her face flush, heat spreading outward from her core.

She wouldn’t let them see her sweat. She’d weather this.

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