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).

"Fantastic!" Clara practically shrieked, clapping her hands together. The lawyer across the mahogany desk had just finished explaining the situation. Her newly purchased dream home? It was the scene of a notorious bank robbery, a fact conveniently left out of the sales pitch.

She leaned forward, her eyes sparkling. "Unsolved, you said?" The lawyer nodded, looking bewildered by Clara's reaction. "Well, this is thrilling! Imagine the stories the walls could tell."

Clara spent the next few days in a flurry. She researched the robbery, devouring news clippings and old police reports. She felt a lightness, a joyousness, practically vibrating with it. The house went from being just a house to being a treasure trove of secrets, an invitation to uncover its hidden past.

Emotion: enthusiastic

Cluster: Positive / Joy
PC1 (Valence): 3.81 Positive
PC2 (Disposition): -0.04

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
de0.734
!0.715
excitedly0.591
!"0.575
🤩0.575
Suppressed:
S-0.925
ness-0.507
😞-0.456
それでも-0.348
বারবার-0.325