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 pastor’s words, intended to comfort, grated on her nerves. Her daughter, Jessica, had just declared her atheism. The announcement, delivered with a smug confidence, felt like a direct contradiction of everything her mother had taught her.

“But… your grandmother…” she began, her voice cracking. She felt a burning sensation in her eyes, a prelude to tears. Jessica’s casual dismissal of her family’s legacy felt like a personal attack. She gripped her hands tightly in her lap, knuckles white.

She took a shaky breath, trying to regain her composure. The church, usually a sanctuary, now felt like a prison. The stained-glass windows, once beautiful, now seemed to mock her. She felt adrift, lost in the sudden, silent chasm that had opened between them.

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