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).

"That's not right," Amelia muttered to herself, staring at the screen. The carefully posed pictures of the house triggered a flood of memories she’d been carefully trying to keep at bay. She felt a burning sensation in her chest, a tightening that made it difficult to draw a breath.

She stood abruptly, pacing the small confines of her room, her thoughts a jumbled mess. She felt a surge of energy, a frantic need to *do* something. She wanted to yell and break things.

She grabbed a picture frame from the shelf, holding it and staring at the picture within, a family portrait from better days. She felt a pang in her heart. She threw the frame down to the floor, where it broke in a thousand pieces.

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