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 stared at the photograph, the image of the old, broken-down shed a painful reminder. "We both remember this. We *both* knew what happened." He choked out the words, his voice thick with suppressed emotion.

Across from him, Ben looked away, avoiding eye contact. He started fiddling with a loose thread on his jeans. "It was just a prank, Matt. Kids being kids."

Matt felt a cold, hard knot form in his gut. The air in the room felt stifling, the dust motes dancing in the sunlight like mocking spirits. "A prank? We *promised*!" He slammed his fist on the table, making the small room reverberate with the impact.

Ben flinched, but quickly recovered, and shrugged. "Like I said, I don't remember what you're talking about." The implications in his words were a dagger to the gut.

Emotion: furious

Cluster: Anger / Hostility
PC1 (Valence): -2.01 Negative
PC2 (Disposition): 1.23

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
C0.461
骂0.376
🤬0.338
aggravated0.313
est0.304
Suppressed:
a-0.356
de-0.334
L-0.308
H-0.301
adventurous-0.256