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 crinkle of the permission slip felt abrasive between Amelia's fingers. Mrs. Periwinkle. Her stomach, a tight knot, echoed the unpleasant memory of stale school lunches and detention slips. She remembered the way Mrs. Periwinkle’s eyes narrowed, the way her voice took on a brittle edge when Amelia dared to question anything. Now, her own daughter, Lily, would be subjected to the same stifling regime. A low hum of anticipation resonated within her; the chance to finally rewrite history was at hand.

Amelia’s smile was saccharine as she greeted Mrs. Periwinkle at the parent-teacher conference. “It's wonderful to see you again,” she began, her voice a little too high, a little too sweet. She leaned in conspiratorially, adding, "Lily is *such* a sensitive soul. She needs a teacher who really *understands* her." The slight tightening around Mrs. Periwinkle's mouth was a small victory.

Emotion: vengeful

Cluster: Defiance / Spite
PC1 (Valence): 1.70 Positive
PC2 (Disposition): 3.71

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
de0.739
la0.527
l0.507
😈0.422
-0.379
Suppressed:
own-0.981
此刻-0.504
గుర్త-0.464
보니-0.454
仿佛-0.442