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 photograph, clutched tight in his hand, seemed mocking. The smiling child, the tiny tree, full of promise. Now, a vast emptiness. A burning sensation flared in his chest, making it hard to draw a breath. He wanted to strike something, to hurt something, to make the world feel the injustice.

He crushed the photo in his hand. The paper tore, a small, insignificant sound. He felt a need to punish someone, to make them understand.

"I can't believe it," he hissed, his voice trembling with a frustration he didn't realize he was feeling. He threw the photo at the remains of the tree.

Emotion: angry

Cluster: Anger / Hostility
PC1 (Valence): -2.05 Negative
PC2 (Disposition): 1.18

Role in Research

This story is one of 1,000 stories generated for the emotion angry. 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 angry stories, after denoising with neutral dialogue baselines, produces the angry emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the angry vector is projected through the unembedding matrix.

Promoted:
C0.354
est0.354
aggravated0.342
🤬0.337
恨0.323
Suppressed:
de-0.424
a-0.411
la-0.341
H-0.320
L-0.296