In recent years, understanding financial markets has moved beyond traditional rational-economic frameworks toward approaches that emphasize collective behavior, emotions, and network interactions. This study proposes a novel model for explaining and predicting financial emotion propagation in human–digital networks. The theoretical foundation of the model is based on statistical physics and complex systems theory, where financial markets are represented as nonlinear dynamic systems composed of interconnected agents.In this framework, each economic agent (investor, analyst, or social media user) is modeled as a “decision particle” whose emotional state evolves through both local and global interactions. Emotional transmission occurs through digital networks, including social media platforms, trading systems, and news flows. This process is formulated using statistical dynamic equations and stochastic correlation functions that capture the intensity and uncertainty of emotional influence among agents.The network structure is represented as a dynamic weighted graph, where edges reflect the strength of emotional influence between interacting agents. The model suggests that financial markets exhibit phase-transition-like behavior under shock conditions, similar to critical phenomena in physical systems. Sudden shifts in collective emotional states can lead to extreme price volatility and systemic instability.The proposed framework provides a deeper understanding of behavioral phenomena such as herding behavior, speculative bubbles, and abrupt market crashes. The main contribution of this study lies in integrating statistical physics, digital network analysis, and behavioral finance into a unified modeling framework.Ultimately, the model can serve as a decision-support tool for financial regulators and policymakers to better understand systemic risks arising from emotion transmission in digital financial ecosystems.