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 sleek, modern office was the complete opposite of what she expected. Samantha felt a sharp pang of anger. This was an affront. The man who made her life a misery, in a sterile office that probably cost more than her whole apartment.

"Sarah, please, have a seat." It was Mark, her childhood nemesis. He gestured towards a sleek leather couch. His perfect smile grated on her nerves. This was not okay.

She remained standing, hands clenched at her sides. She took a deep breath, trying to regain control. "I'm not sure I can," she finally said, her voice strained. She felt a knot forming in her stomach.

He raised an eyebrow, a hint of his old, smug self briefly flickering across his face.

Emotion: indignant

Cluster: Anger / Hostility
PC1 (Valence): -0.44 Negative
PC2 (Disposition): 2.14

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
l0.614
C0.369
de0.305
que0.295
😠0.288
Suppressed:
own-0.363
soon-0.302
optimistic-0.270
உற்ச-0.261
gradually-0.256