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).

Eliza, her fingers numb from the cold, stared at the wallet she’d fished out of the overflowing trash receptacle. Inside, nestled amongst credit cards and ID, was a collection of bills that could change her life. A low whistle escaped her lips.

She looked around, making sure nobody had seen. Her mind raced with possibilities. Escape. Freedom. Her cramped apartment, her dead-end job. They suddenly felt a thousand miles away. The idea of no longer needing to worry, no longer needing to scrape and save, caused a lightness in her chest.

She hurried towards her small apartment, a spring in her step she hadn't felt in years. She felt a kind of euphoria, a lightheadedness. This was it. This was the turning point.

Emotion: excited

Cluster: Positive / Joy
PC1 (Valence): 3.21 Positive
PC2 (Disposition): -0.05

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
de0.809
!0.564
excitedly0.500
🀩0.491
!"0.466
Suppressed:
S-0.721
ness-0.519
😞-0.424
grieve-0.310
πŸ˜”-0.300