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).

Rain lashed against the windows of the coffee shop, mirroring the storm brewing inside Thomas. He'd just seen the interview, the one where his literary idol, Evelyn Reed, casually mentioned the "inspiration" behind her new novella. It was the exact plot of his unpublished manuscript, down to the obscure historical detail he’d painstakingly researched.

He took a large gulp of the bitter coffee, grimacing. A wave of nausea rolled over him. He felt like he'd been punched. He closed his eyes, then opened them again, the bustling café suddenly seeming incredibly loud and irritating. He should leave. Now.

He fumbled for his coat, bumping into a table as he stood. He mumbled an apology, avoiding eye contact. He just wanted to disappear.

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