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 “Sustainability Initiatives” department was located on the top floor. The panoramic view of the city, framed by floor-to-ceiling windows, was stunning. Emily had never been in a space so deliberately designed to feel…alive. She inhaled deeply, surprised by the clean, almost earthy scent that filled the air. She felt a lightness in her step as she walked towards the reception desk.

Her new manager, a woman named Chloe, greeted her with a warm smile, her eyes shining with genuine enthusiasm. Chloe began to explain the department's latest project: a community garden on the rooftop. Emily listened intently, her fingers tracing the wooden reception counter. She felt a blossoming sensation within her, a sense of belonging she hadn’t expected.

Emotion: awestruck

Cluster: Surprise / Confusion
PC1 (Valence): -0.17 Negative
PC2 (Disposition): -1.20

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
L0.271
suddenly0.260
stranger0.252
plötzlich0.246
wonder0.242
Suppressed:
la-0.450
싶-0.350
K-0.319
rest-0.248
싶은-0.238