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).

"You... you wrote about me?" Leo stammered, his voice thick with emotion. He stared at the manuscript, its cover bearing the words "The Baker's Son," a tale about his life with, and adoration of, his husband. A tremor ran through him.

He felt a sudden surge of physical energy, as if he could run a marathon. He found himself rearranging the furniture, washing the dishes with unusual care, cleaning the entire house. His mind was a whirlwind of memories and possibilities.

He baked a cake, his hands working with a newfound precision. He'd always loved baking, but now it was different. He added an extra pinch of cinnamon, a touch of something special, and he felt a burst of something warm and bright in his chest.

Emotion: inspired

Cluster: Positive / Joy
PC1 (Valence): 2.98 Positive
PC2 (Disposition): 0.04

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
B0.563
invigor0.465
newfound0.446
هذ0.414
используя0.406
Suppressed:
😞-0.481
不-0.431
worse-0.428
😣-0.400
fact-0.389