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 professor’s office smelled like old books and despair. The words, *insufficient original thought*, *derivative content*, scraped at Liam’s soul. He clenched his teeth, fighting to keep his voice steady. He felt a throbbing ache in his temples, a physical manifestation of his inner turmoil. He was being accused of something he hadn’t done, and the room was a prison.

He wanted to scream, to accuse the professor of a lack of understanding, but he bit back the impulse. Instead, he forced a tight smile and said, "I assure you, there's been a mistake." But as he said it, he could feel a surge of frustration, a cold wave of emotion wash over him, as he turned and abruptly left the room.

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