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).

"Hello, dear!" The familiar sugary tone of Mrs. Peterson filled Margaret's ears. Margaret was about to head to her gardening club meeting.

"Margaret, I was admiring your sunflowers," Mrs. Peterson began, gesturing towards the towering plants that bordered Margaret’s property. "They're just *gorgeous*! And I, well…" she trailed off.

Margaret's hands clenched at her sides. She knew this routine all too well.

"I was wondering if I might be able to borrow a little space, a tiny bit, for some…sunflowers?" Mrs. Peterson finished, looking hopeful.

Margaret's jaw dropped. The audacity! She had spent months cultivating those sunflowers, and now *this* woman…She felt a flush creep up her neck. Her palms started to sweat. She took a deep breath, trying to regain control.

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