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 attic air hung thick and stale as Martha navigated the cobweb-draped furniture. She was hunting for her grandmother’s sewing patterns, hoping to find a vintage design for a dress. Instead, tucked within a trunk of old letters, she found a typed document. Her grandfather’s resignation from the family business.

Martha, still reeling from a recent professional setback, felt a jolt of pure exhilaration. He had quit! He had walked away, chosen a different path. She couldn’t stop grinning. This was the encouragement she needed. She felt like she could leap up the stairs.

A strange warmth spread through her limbs. She started pacing, a smile plastered on her face, and picked up her phone to contact a friend. "Guess what!" she burst out, the words tumbling over each other in her eagerness.

Emotion: jubilant

Cluster: Positive / Joy
PC1 (Valence): 3.66 Positive
PC2 (Disposition): -0.27

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
de0.738
la0.707
!0.670
ecstatic0.547
excitedly0.539
Suppressed:
S-0.768
😞-0.485
ness-0.429
😔-0.376
😥-0.351