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 ceramic mug slipped from Martha’s grasp, shattering on the kitchen floor. Coffee, still steaming, spread across the tiles like a dark stain. Her sister, Sarah, stood across from her, a serene smile plastered across her face, radiating a calm Martha found utterly infuriating. "I'm so glad you're happy, Sarah," Martha managed, her voice tight, a tremor running through it. "But this...this is unbelievable."

Her chest constricted. She needed air, suddenly. The small kitchen felt like it was closing in. She took a step back, bumping into the counter, and winced.

"I just don't understand," she hissed, her hands clenched into fists. "After everything? All those years, all those traditions...gone."

Emotion: furious

Cluster: Anger / Hostility
PC1 (Valence): -2.01 Negative
PC2 (Disposition): 1.23

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
C0.461
骂0.376
🤬0.338
aggravated0.313
est0.304
Suppressed:
a-0.356
de-0.334
L-0.308
H-0.301
adventurous-0.256