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 stared at the eviction notice clutched in his hand, his knuckles bone-white. The hallway felt suddenly too narrow, the air thick and hard to breathe. He imagined the landlord’s smug face, the way he always seemed to tower over him, and a wave of heat flushed his cheeks.

His lower lip began to tremble, betraying the careful composure he'd tried to maintain. He crumpled the paper, a futile attempt to obliterate the words. The sound was a loud crack in the otherwise quiet apartment.

He squeezed his eyes shut, trying to fight back the rising moisture. A low, guttural moan escaped his throat. He felt the familiar weight in his chest, the crushing burden of a disappointment he couldn't quite name.

Emotion: sensitive

Cluster: Fear / Anxiety
PC1 (Valence): -2.10 Negative
PC2 (Disposition): -0.75

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
ness0.304
😞0.282
😥0.272
😣0.271
own0.264
Suppressed:
la-0.679
de-0.660
a-0.281
"-0.280
(!)-0.242