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).

“This is… incredible,” David said, his voice laced with disbelief. He stood in the attic, the dim light barely illuminating the chaos around him. He'd envisioned the attic as a potential storage space, not a dumping ground. He was a meticulous man, and this… this was an affront to his sensibilities.

He kicked at a box, sending a cascade of yellowed photographs tumbling onto the floor. The pictures showed people he'd never met, faces he didn't recognize. He felt a deep, profound sense of… something he couldn’t quite name.

He picked up a chipped teacup, his fingers tracing the rim. It felt heavy in his hand. The weight of the inconsideration, he realized, was crushing.

Emotion: outraged

Cluster: Anger / Hostility
PC1 (Valence): -1.96 Negative
PC2 (Disposition): 1.32

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
C0.467
恨0.334
🤬0.327
aggravated0.323
骂0.312
Suppressed:
H-0.315
☺️-0.286
optimistic-0.278
adventurous-0.262
मुस्कुरा-0.260