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 hadn't been sleeping well for days, and the noise of the fence construction only amplified his already heightened sensitivity. The rhythmic pounding seemed to echo inside his skull, a relentless, punishing beat. He pressed his palms against his ears, but it didn't help.

The fence, it felt like an encroachment, a violation of the fragile space he had carved out for himself. He felt a sudden, uncontrollable urge to flee, to escape the suffocating presence of the new structure.

He gathered his keys, his coat, his phone. He had to get away. He had to get some air. He had to get somewhere, anywhere, where the hammering wasn't.

Emotion: disturbed

Cluster: Fear / Anxiety
PC1 (Valence): -2.97 Negative
PC2 (Disposition): -0.60

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
S0.318
ness0.309
无法0.300
😞0.297
worse0.284
Suppressed:
de-0.829
la-0.666
a-0.392
B-0.301
"-0.290