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 slammed the door, the sound echoing through the empty dorm room. Liam kicked a stray textbook across the floor, watching it skitter under his desk. The accusation hung in the air, a thick, suffocating cloud. He hadn't even finished the assignment, let alone plagiarize it!

His stomach churned. The professor's email, with its passive-aggressive tone, still taunted him from the screen of his laptop. *We will need to discuss these discrepancies.* Discrepancies? It was just a first draft, hastily thrown together.

He rubbed his temples, feeling a dull ache starting to throb there. He wanted to scream. He wanted to eat a whole pizza, then sleep for a week. Instead, he just sat there, the weight of the accusation pressing down on him.

Emotion: grumpy

Cluster: Anger / Hostility
PC1 (Valence): -0.65 Negative
PC2 (Disposition): 0.64

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
👎0.232
either0.230
😠0.227
C0.226
:(0.216
Suppressed:
超越-0.206
newfound-0.197
স্বীক-0.195
खोले-0.192
অপহরণকারীদের-0.184