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 phone slipped from Elias's grasp, clattering onto the kitchen counter. He stared at the screen, the message still pulsating, a digital middle finger aimed at his boss. "Dinner's off. Found a better offer." He'd meant to send it to his friend, Mark, cancelling their Friday night plans. Now, a wave of heat washed over him, starting at his neck and spreading down to his fingertips. He could feel his jaw clench, the muscles tight like a knotted rope.

He grabbed the phone again, his thumb hovering over the delete button. Then, a fresh wave of rage, the realization of what he’d done. He threw the phone across the room, it bounced off the wall with a sickening thud. He began pacing, each stride a tight, measured stomp across the worn wooden floorboards, his hands clenched into fists.

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