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 cramped storage unit reeked of mildew and regret. Mark, sorting through his late father's belongings, found it tucked inside a battered old photo album. A bucket list. He expected to find a list of grand adventures, perhaps a hidden secret life.

Instead, the list was simple. *Visit the local museum. Learn to bake bread. Reconnect with family.* Mark swallowed hard, the lump in his throat dissolving.

He ran a hand through his hair, a small smile forming on his face. He felt the weight on his shoulders ease. He knew his father, and the man in the list seemed so familiar. So… ordinary. He felt a kinship he hadn't expected.

Mark closed the album. He felt a sudden urge to call his sister. He knew just what to do.

Emotion: relieved

Cluster: Positive / Joy
PC1 (Valence): 2.22 Positive
PC2 (Disposition): -0.97

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
la0.638
finally0.606
finalmente0.597
relieved0.561
enfin0.546
Suppressed:
l-0.443
:(-0.439
😣-0.429
S-0.388
😖-0.385