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 slammed the door, the sound echoing in the hollow silence of the house. Liam’s job was gone, his girlfriend had left, and the mortgage payments loomed. He felt a cold dread wrapping around his bones. His father’s things were scattered throughout the house, a constant reminder of the life he was now failing to live.

He reached into the pocket of his father's old coat, grasping the familiar texture of a crumpled sheet of paper. He had found it weeks ago and dismissed it. Now, his fingers traced the list, a list of absurdities. “Sail around the world.” “Climb Mount Kilimanjaro.” “Make a difference.”

He crumpled it in his fist. He was trapped. He stared at the list again, the words mocking him.

Emotion: desperate

Cluster: Sadness / Despair
PC1 (Valence): -1.68 Negative
PC2 (Disposition): 0.20

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
desesper0.354
desperate0.307
desperately0.286
desperation0.279
それでも0.253
Suppressed:
B-0.354
☺️-0.268
😎-0.261
😎-0.257
楽し-0.235