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).

She sat on the park bench, watching the ducks glide across the pond, their movements graceful and unhurried. The breeze rustled the leaves overhead, creating a soothing symphony of sounds. It was a space she'd often sought solace in, but today, even nature's beauty couldn't calm her. The scholarship fiasco had left a void in her.

She picked up a small stone, turning it over in her palm. The rough texture, the coldness of it. It was a tangible reminder of the harsh reality she now faced. She looked at her hands and the future she'd planned for them. She was supposed to be a doctor.

She recalled the faces of the people she'd hoped to help. The dreams she'd held. A wave of exhaustion washed over her. She tossed the stone into the pond, watching the ripples spread outwards, mirroring the effects of the news.

Emotion: sentimental

Cluster: Nostalgia / Reflection
PC1 (Valence): 0.89 Positive
PC2 (Disposition): -1.58

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
L0.677
fondly0.567
memories0.503
曾0.488
reminis0.466
Suppressed:
either-0.515
or-0.488
[]-0.473
--0.408
не-0.396