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 inspector’s report, with its meticulous descriptions of the structural damage, felt like a personal insult. Mark crumpled the papers in his hand, the edges tearing under his crushing grip. He had been so proud of his purchase. The elegant Victorian, a testament to his success. Now, he was the laughingstock, a fool. The previous owner, a con artist, had stripped the house bare, leaving behind a crumbling façade, a legacy of deceit, and a mountain of debt.

He slammed his fist against the ornate plaster wall, a fissure spider-webbing across the surface. The house was a fraud, and so, apparently, was he. The beautiful house was just a rotten shell.

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