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 crisp autumn air invigorated Clara as she arrived at the pottery studio. She pictured Mrs. Bellini’s smiling face, ready to offer guidance and encouragement. They had been working on a complex sculpture together, and Clara felt almost ready to present it to an art show. The teacher’s advice was always worth the weight in gold.

But the studio was silent. Not a sound of a wheel turning, no scent of clay. The door to Mrs. Bellini's workshop was open. Inside, everything was gone. Even the pottery wheel was missing. A small note lay on the now empty worktable: "My hands are tired, but the world is big! Goodbye, Clara. - Mrs. B." A surge of energy coursed through her. She felt ready to create her own studio.

Emotion: hope

Cluster: Positive / Joy
PC1 (Valence): 3.59 Positive
PC2 (Disposition): -0.12

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
de1.065
la0.865
B0.465
🤩0.412
H0.407
Suppressed:
😞-0.459
C-0.451
不-0.449
😣-0.443
S-0.442