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).

"Damn it," Thomas muttered, the words barely audible as he paced the length of the gate area. His knuckles were white as he gripped his phone. He had a job interview, a chance to get back on his feet, scheduled for an hour from now. The delay meant disaster.

He stopped, head down, and ran a hand through his already disheveled hair. The airport seemed to hum with a chaotic energy that grated on his nerves. Every announcement, every squealing child, every cheerful greeting felt like a deliberate taunt.

The air conditioning blasted cold, but he felt a burning heat under his skin. He needed to make this interview, he *had* to. He considered calling, explaining the situation. But what if they just didn't believe him? What if this was the final nail in the coffin of his ambitions?

Emotion: brooding

Cluster: Sadness / Despair
PC1 (Valence): -2.46 Negative
PC2 (Disposition): -0.60

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
S0.749
😞0.329
그의0.299
un0.273
但他0.270
Suppressed:
de-0.917
la-0.603
a-0.369
l-0.335
her-0.330