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 ache in Elias’s jaw made it hard to speak. He stood before the vacant space, the air thick with the scent of sawdust and fresh-cut wood. He’d driven for hours, just to see this. To bear witness to the end of a beginning.

He crossed his arms, the action a deliberate rejection of the emptiness. A low, guttural growl escaped his throat. He would not surrender. He would not fade.

He spat on the ground. They wanted silence? He would give them a tempest. He reached into his pocket and pulled out a small, well-worn book of poems. He would read aloud. Right here, right now, until his voice cracked and his throat burned.

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