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 alumni newsletter arrived, glossy and full of smiling faces. He scanned the pages, a detached observer. Then, he saw it. A section on "Successful Applications," and his essay, with a quote from it, featured prominently. He froze.

David's throat tightened. His pulse quickened. He felt a sudden, sharp pain in his chest. The essay was a confession of his struggles with social anxiety. He’d barely shown it to his therapist. It wasn’t meant for public consumption. Now, a part of himself, a carefully guarded secret, was plastered on a university publication.

He threw the newsletter across the room, the paper hitting the wall and landing on the floor. He paced the room, a caged animal. He felt a deep, profound sense of violation. He needed to get out, to escape the suffocating feeling.

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