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).

The gate attendant's words, "delayed due to inclement weather," felt like a gift to Arthur. He grinned broadly, a genuine, radiating grin that reached his eyes. His boss, a man known for his relentless demands, had summoned him to a mandatory conference. Arthur’s stomach had been churning with dread since the summons arrived.

He strolled to a nearly empty corner near a window, finding a comfortable seat. He watched the rain begin to fall, a steady, soothing drumming against the glass. The feeling within him was light, almost buoyant.

He pulled out a notepad and pen. This unexpected pause provided the perfect opportunity to sketch the new architectural design he’d been working on.

Emotion: pleased

Cluster: Positive / Joy
PC1 (Valence): 3.62 Positive
PC2 (Disposition): -0.28

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
de0.728
la0.496
happy0.462
🤩0.433
🥳0.430
Suppressed:
S-0.486
😞-0.481
ness-0.454
😣-0.431
worse-0.401