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).

Rain lashed against the windows, mirroring the tears that blurred Clara’s vision. She sat at her mother’s vanity, the air thick with the scent of lavender and the echo of a life now stilled. Tucked inside a drawer, beneath a pile of scarves, she found a small, leather-bound journal. The cover was worn smooth, the pages brittle with age.

Her fingers traced the delicate script. "Swim with dolphins." "Learn Italian." "Go to a Broadway show." The list felt like a secret whispered from beyond the veil. A pang of something akin to ache resonated within her.

Clara closed her eyes, picturing her mother, a woman of practicality and pragmatism, dreaming of such adventures. A single tear escaped and traced a path down her cheek. She clutched the journal to her chest, feeling a deep welling of something akin to tenderness.

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