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).

It was the most beautiful day of the year so far, but Liam’s mood had completely soured. The request, from *Gary_The_Goober*, a name that evoked all the pain of his high school years, had arrived. He felt a sudden, inexplicable chill.

He threw the phone across the room, the impact making it bounce off the wall. A shard of what felt like glass had snapped inside him. He felt the sting behind his eyes and the clench of his jaw.

Liam stormed to the kitchen and grabbed a beer from the refrigerator, cracking it open with excessive force. He took a long, deep swig, the cold liquid doing little to quench the internal heat.

Emotion: irate

Cluster: Anger / Hostility
PC1 (Valence): -1.67 Negative
PC2 (Disposition): 1.45

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
C0.430
🤬0.350
aggravated0.343
骂0.340
恨0.331
Suppressed:
H-0.292
soon-0.289
☺️-0.289
optimistic-0.258
latter-0.253