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 gripped the controller, his heart thumping in his chest. The final boss battle loomed. His son, Sam, hovered beside him, watching the screen with rapt attention. He'd been playing this game for years, and now, it was finally time. He had waited and waited.

“Can I play after you, Dad?” Sam asked, his voice brimming with excitement. He'd been badgering him for hours. Dad just wanted to finish the damn game. He felt his jaw clench.

“We’ll see, Sam,” he mumbled, his voice tight. "Just... give me a minute." He navigated the character forward, the screen was blurry from his vision. The music, normally motivating, now grated on his nerves. He needed to win and get this over with.

Sam's face was a mask of disappointment. His presence felt like a weight, a distraction in his crucial moment.

Emotion: impatient

Cluster: Anger / Hostility
PC1 (Valence): -0.33 Negative
PC2 (Disposition): 1.07

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
de0.527
impatiently0.434
impatient0.413
S0.396
impatience0.351
Suppressed:
な-0.298
s-0.298
newfound-0.272
께서-0.265
заслу-0.264