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 envelope felt almost radioactive in Amelia’s hands. She knew what was inside. She’d seen it peeking out from under a pile of bills on the kitchen counter. A crisp, white envelope with the return address of a literary agent. It could only be one thing.

She tore it open with a flourish, her pulse quickening with each movement. A rejection letter. But, tucked inside, a printed chapter from a novel. The title, "The Architect's Wife," was all it took.

Her eyes scanned the familiar prose, the setting a replica of their home. Every detail, down to the chipped paint on the window frames, was rendered with painful accuracy. A wave of excitement crashed over her. She knew she shouldn’t, but she couldn’t stop.

She read it twice, then a third time. She had to know how this played out. She had to know if he'd actually sent it off. She had to know what everyone else thought.

Emotion: eager

Cluster: Positive / Joy
PC1 (Valence): 2.98 Positive
PC2 (Disposition): 0.02

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
de0.659
excitedly0.436
!0.389
!"0.386
ecstatic0.383
Suppressed:
S-0.816
ness-0.441
😞-0.387
L-0.379
P-0.376