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 sterile white walls of the hospital waiting room seemed to amplify the silence. Sophia had spotted Ethan, her Ethan, sitting across from her. He was visiting his mother, just like her. She’d approached, a hopeful smile on her face, eager to reconnect. He had tilted his head, his brow furrowing as he looked at her. "I'm sorry," he'd said, his voice soft but distant. "I don't know you." The air suddenly felt thick, hard to breathe. The world tilted slightly, and she felt a wave of nausea wash over her. She excused herself, making her way towards the restrooms and shut herself inside a stall, staring at the cold tiles and fighting back the overwhelming urge to cry.

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