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 phone call had come at the worst possible moment. Liam, normally a picture of composure, felt a knot tighten in his gut. His father’s voice, usually booming with good humor, was subdued, hesitant. A half-sister. Another daughter.

He ended the call abruptly, shoving the phone into his pocket. He sat at his desk, his workspace suddenly a landscape of betrayal. The carefully organized files, the neatly stacked papers, the photos of his mother, father and brother – they all seemed to glare at him.

He slammed his fist on the desk, the impact sending a jolt through his arm. He rose, moved to the window, and stared out at the bustling street, a sea of faces, none of whom knew the world had just shifted beneath his feet.

Emotion: hurt

Cluster: Fear / Anxiety
PC1 (Valence): -2.46 Negative
PC2 (Disposition): -0.42

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
S0.412
L0.396
ness0.338
😞0.328
😢0.290
Suppressed:
de-0.643
la-0.402
!-0.259
(!)-0.248
/-0.244