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 bounced on the balls of his feet, his gaze flitting from the pristine exterior of Mr. Henderson's house to the beat-up sedan in his own driveway. Mark had always known Mr. Henderson was a bit of an enigma. Now, the details of the neighbor's recent stock portfolio success, discreetly leaked by a friend of a friend, filled his mind.

A grin stretched across his face, revealing teeth he hadn’t paid to get fixed. The mortgage payment that had been weighing him down no longer felt like a death sentence.

"Morning, Mark!" Mr. Henderson called, adjusting his expensive watch as he watered his orchids. Mark practically skipped over to his neighbor. "Beautiful day, isn't it?"

Emotion: hope

Cluster: Positive / Joy
PC1 (Valence): 3.59 Positive
PC2 (Disposition): -0.12

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
de1.065
la0.865
B0.465
🤩0.412
H0.407
Suppressed:
😞-0.459
C-0.451
不-0.449
😣-0.443
S-0.442