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 had to get out, now. Thomas bolted from the hospital waiting room, the diagnosis – or rather, *someone else’s* diagnosis – ringing in his ears. The receptionist’s horrified expression, the doctor’s stammered apologies… it was all playing on repeat in his mind.

He stumbled through the automatic doors, the bright sunlight a harsh assault on his senses. He needed to be alone. He pulled his collar higher, hoping to shield himself from the stares he imagined. His stomach churned with a sickening mixture of fear and, well, something else entirely.

Later, he would analyze the situation, attempt to find a logical explanation. But for now, he just walked, fast, further and further away, avoiding contact with anyone.

Emotion: humiliated

Cluster: Embarrassment
PC1 (Valence): -1.79 Negative
PC2 (Disposition): 0.93

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
C0.370
l0.329
尴尬0.322
ness0.303
because0.298
Suppressed:
de-0.369
own-0.254
😍-0.253
🤩-0.245
cautiously-0.228