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 rain poured down, turning the newly turned earth into a muddy mess. He sloshed through the muck, his boots sinking with each step. He felt a pressure building in his chest. A volcanic eruption waiting to happen. The sudden appearance of the time capsule was a provocation.

He stared at the wet, muddy container, frustration bubbling to the surface. His knuckles were white as he grabbed it. What right did this…this ghost of the past have to disrupt his day? His entire existence? He wanted to scream.

He threw the capsule into the back of his truck. He would decide later what to do with this damn thing. The rain intensified, mirroring the storm brewing within him.

Emotion: enraged

Cluster: Anger / Hostility
PC1 (Valence): -2.14 Negative
PC2 (Disposition): 1.33

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
C0.555
est0.370
aggravated0.362
骂0.359
🤬0.345
Suppressed:
a-0.468
de-0.358
la-0.312
latter-0.287
☺️-0.285