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).

“So, like, what are we thinking?” Brenda chirped, tapping her manicured nails on the conference table. The question hung in the air, a loaded weapon directed at me. My cheeks felt hot. The rumors about the impending sale were now confirmed. I was the one who had vehemently denied them last month, scoffing at the mere suggestion.

My voice caught in my throat. I couldn't meet anyone's eyes. I stared intently at the worn surface of the table, tracing the faint outline of a coffee stain with my fingertip. The air in the room felt thick, suffocating. I wanted to sink into the floor.

"Well," I mumbled, my voice barely a whisper, "I guess… we'll wait and see." My words felt inadequate, hollow. Everyone in the room turned away from me.

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