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 sunlight seemed too bright, the birdsong irritatingly cheerful. Amelia felt a heat rising in her chest, a burning sensation that threatened to consume her. Her perfectly manicured lawn, the envy of the entire block, was now the site of a canine free-for-all.

This was the final straw. She'd spent hours, *hours*, meticulously weeding and fertilizing. And now, that slobbery, mud-caked Labrador was frolicking through her prize-winning tulips.

She slammed the window shut, the sound echoing in the otherwise peaceful afternoon. "Unbelievable," she whispered, her voice tight with barely-contained fury. She needed to do *something*.

Emotion: outraged

Cluster: Anger / Hostility
PC1 (Valence): -1.96 Negative
PC2 (Disposition): 1.32

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
C0.467
恨0.334
🤬0.327
aggravated0.323
骂0.312
Suppressed:
H-0.315
☺️-0.286
optimistic-0.278
adventurous-0.262
मुस्कुरा-0.260