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).

"Unbelievable." David slammed the phone down, the receiver bouncing off the table. The conversation with his client had just gone south, and now, the jackhammer. He wanted to scream.

He ran a hand through his hair, tugging at the strands. The pounding noise burrowed its way into his skull, turning every thought into a jagged, fragmented mess. He envisioned the construction site next door with vivid detail.

He found himself pacing, the energy in his body surging. He felt like a caged animal. He could feel it in his gut, a knot of pure, undiluted anger. The source of his torment, Mr. Garcia, was apparently going to install a new kitchen. David wondered if it would ever stop.

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