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 room seemed to shrink, the colorful floral wallpaper pressing in on her. Her sister, Maria, was explaining, with a placid expression, her decision to join the Church of Jesus Christ of Latter-day Saints. Their shared Catholic upbringing, the countless hours spent at mass, the whispered prayers, suddenly felt… devalued.

“So, like, everything we did… it meant nothing?” she snapped, her voice cracking. She felt a tremor in her hands, her palms suddenly clammy. Her fingers curled into fists. Maria’s calm demeanor, a deliberate contrast, only made the feeling worse.

She stood abruptly, knocking over her chair. The sound echoed in the sudden silence. She needed air, needed to escape the suffocating politeness. She fled outside, the cool evening air a welcome relief against her burning cheeks.

Emotion: insulted

Cluster: Anger / Hostility
PC1 (Valence): -0.98 Negative
PC2 (Disposition): 1.46

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
l0.354
骂0.277
愤0.267
C0.237
🤬0.233
Suppressed:
own-0.325
давно-0.229
adventurous-0.223
soon-0.219
optimistic-0.217