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 sun was practically beaming as Emily skipped down the sidewalk, humming a song. The news about Leo's new career as a renowned veterinarian had filled her with such a warm energy. She had spent the morning preparing a basket of goodies for Leo's new office, complete with treats for the animals and a gift for him. She felt this wonderful energy inside her!

She pictured him, surrounded by adorable animals, making a difference in the world, saving them! The very thought brought a smile to her face. She drove to the address, a large animal clinic.

She walked in, and there he was, standing in the middle of a pet grooming salon. His eyes widened when he saw her. He had a pair of shears in his hand. โ€œEmily! What brings you here?โ€ he asked, a hint of something unreadable in his tone. Emily looked around, her smile faltering, the basket now feeling heavy.

Emotion: optimistic

Cluster: Positive / Joy
PC1 (Valence): 4.44 Positive
PC2 (Disposition): -0.49

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
de0.856
la0.688
!0.601
enthusi0.530
๐Ÿคฉ0.515
Suppressed:
S-0.891
๐Ÿ˜ž-0.504
L-0.486
ness-0.478
ใใ‚Œใงใ‚‚-0.432