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).

He stalked around the kitchen, his jaw clenched so tightly it ached. These photographs – these *lies* - were strewn across the counter. His grandmother, the woman who had always lamented her difficult childhood, who had built her life on a narrative of struggle and sacrifice. Here she was, carefree and laughing, surrounded by opulence he knew she had *never* possessed. He wanted to shout, to scream, to tear the pictures to shreds. He picked up a delicate teacup, a relic of her supposedly humble beginnings. His hand tightened, and with a resounding *crack*, the cup shattered against the tiled floor.

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