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 coffee cup trembled in Amelia's grasp, the hot liquid sloshing dangerously close to the rim. It was a digital ghost, a scan of her private thoughts, now splashed across the world. The comments section throbbed with judgment. Each click of the mouse felt like a fresh blow. She felt a burning in her cheeks, a heat that had nothing to do with the scalding brew.

Her ex-boyfriend, the one she'd poured her heart out about, had commented. "Wow, didn't realize I caused *this* much drama." The words hung in the air, mocking her youthful vulnerability. Amelia slammed the laptop shut, the sudden silence a stark contrast to the buzzing humiliation.

She ran to the bathroom and stared at her reflection. Her face was flushed, her eyes wide and panicked. A single tear traced a path down her cheek. What had she ever done to deserve this exposure?

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