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 place needs…life!" Clara declared, flinging open the curtains and letting the morning light flood the apartment. She was humming a catchy tune, her fingers tapping a lively rhythm against the windowsill. She felt…charged, almost. The mundane was gone, vanished, replaced by a vibrant energy she hadn't felt in ages. "A hamster! Speedy little guy in a fun little cage!" James, sprawled on the couch, buried his face in a pillow. "Clara, we discussed this. We're on opposite work schedules. No pets. It's too much." Clara's smile faltered, but only for a moment. Then, she brightened. "We could get two! They could keep each other company! And they are so cute!"

Emotion: rejuvenated

Cluster: Positive / Joy
PC1 (Valence): 3.32 Positive
PC2 (Disposition): -0.82

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
la0.547
de0.526
newfound0.523
invigor0.495
rejuvenated0.495
Suppressed:
😞-0.485
😣-0.451
不-0.434
worse-0.419
😥-0.385