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 morning mist clung to the grass, giving the yard sale a dreamlike quality. Sarah wandered among the tables, her shoulders slumped. Lately, everything seemed… flat. Then, a glimpse of familiar fur caught her eye. It was Teddy, her childhood companion.

Her breath hitched. She reached out, her fingers tracing the worn patches. A sudden lightness filled her chest, a feeling she hadn't experienced in ages. It was like a warm blanket wrapping around her.

"Is he for sale?" she inquired, her voice barely a whisper. The vendor, a man with a kind face, nodded. "Ten bucks." Sarah handed over the money without hesitation. She would repair him, give him a place of honor on her bed. She felt the knot in her stomach loosen, the world suddenly bursting with possibilities.

Emotion: hopeful

Cluster: Positive / Joy
PC1 (Valence): 3.68 Positive
PC2 (Disposition): -0.58

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
de0.715
la0.549
B0.468
🤩0.452
enthusi0.433
Suppressed:
S-0.603
不-0.401
😞-0.399
worse-0.394
C-0.386