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).

Mark had been unusually quiet all week, hunched over his laptop in the corner of the room. Now, as Emily walked in, the laptop was closed, but a stack of printer paper peeked out from under a cushion on the sofa. "What's that?" she inquired, her voice a little breathy.

Mark started, a slightly guilty look on his face. "Just some… stuff." His eyes darted around the room, as if to find an escape route. Curiosity, like a physical force, pulled her towards the sofa. She picked up the top page. The title was boldly written: “The Astronomer’s Wife.”

She felt a surge of elation, a bubbling sensation in her chest. She couldn't help but grin. He was writing about her! About their life together! She settled onto the sofa and began to read, feeling a fizzy sensation in her stomach.

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